© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15238
    Prev
    Next
    INDEX
    Explanations

    words related to code, data structures, and game entities

    oai_token-act-pair · gemini-2.0-flash

    code, data structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    DockStyle
    -0.73
    endpush
    -0.68
    fromCharCode
    -0.64
    setminus
    -0.64
    цездатний
    -0.64
     doInBackground
    -0.59
    endsection
    -0.57
    ℗
    -0.57
    __((
    -0.56
     onCreateView
    -0.54
    POSITIVE LOGITS
     ExecuteAsync
    0.63
    CloseOperation
    0.52
     समीक्षक
    0.50
    ագրություններ
    0.48
     Feste
    0.46
    ingly
    0.44
    αρα
    0.42
    ustom
    0.42
    Jeografia
    0.42
     AspNetCore
    0.41
    Activations Density 11.232%

    No Known Activations