© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7445
    Prev
    Next
    INDEX
    Explanations

    varied; the neuron activates for "into high" and "at full", but also activates for what appears to be highly specific jargon about vehicle gears. The neuron activates for phrases that indicate intensity or full capacity, but can also activate for content about cars.

    oai_token-act-pair · gemini-2.0-flash

    gear-related terminology

    np_token-act-pair-logits · gpt-4o-mini

    transmission gears

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yargs
    -0.49
     riz
    -0.45
    CreateMap
    -0.45
     CreateTagHelper
    -0.44
     gallery
    -0.43
    KommentareTeilen
    -0.43
    VStack
    -0.43
    Glob
    -0.43
    bai
    -0.42
    msgTypes
    -0.41
    POSITIVE LOGITS
     gear
    0.99
     overdrive
    0.92
     Gear
    0.81
     الحره
    0.81
     GEAR
    0.77
    gear
    0.75
    Gear
    0.75
     gears
    0.71
     autopilot
    0.68
     متعلقه
    0.65
    Activations Density 2.039%

    No Known Activations