© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6461
    Prev
    Next
    INDEX
    Explanations

    technical terminology from chemistry, physics, and computer science

    oai_token-act-pair · gemini-2.0-flash

    polymer science

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     Charles
    -0.54
     Bell
    -0.50
    Clark
    -0.50
    AYSIA
    -0.50
     lenker
    -0.49
    رشف
    -0.49
    bell
    -0.48
    Bell
    -0.48
    __(/*!
    -0.48
     mahdollis
    -0.47
    POSITIVE LOGITS
     AppBundle
    0.70
    DebuggerStep
    0.64
     InputDecoration
    0.64
    CreateMap
    0.63
     تانيه
    0.62
    Atsauces
    0.60
    :✨
    0.58
     BoxFit
    0.57
    feinander
    0.55
    UnusedPrivate
    0.55
    Activations Density 13.269%

    No Known Activations