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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 490
    Prev
    Next
    INDEX
    Explanations

    words relating to wearable protective equipment, particularly for the ears, elbows and knees

    oai_token-act-pair · gemini-2.0-flash

    body parts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ImageContext
    -0.67
     AssemblyCompany
    -0.63
    GeneratedMessage
    -0.61
    NgModule
    -0.60
    writeField
    -0.58
     חיצוניים
    -0.56
     BoxFit
    -0.55
     propOrder
    -0.55
    IsMutable
    -0.54
    новништво
    -0.53
    POSITIVE LOGITS
     Baillargeon
    0.52
    klä
    0.48
    cons
    0.48
    Kons
    0.47
     Donuts
    0.47
     Vive
    0.46
     Costello
    0.46
    hatch
    0.45
     Kons
    0.45
    clothes
    0.45
    Activations Density 6.762%

    No Known Activations