© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9955
    Prev
    Next
    INDEX
    Explanations

    parts of source code, including code comments, imports and auto-generated code warnings

    oai_token-act-pair · gemini-2.0-flash

    code generation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    makeConstraints
    -0.93
     فريبيس
    -0.84
    ReusableCell
    -0.77
    Hentet
    -0.74
    ConstraintMaker
    -0.72
     виправивши
    -0.72
    IntoConstraints
    -0.71
     snippetHide
    -0.70
     مشين
    -0.69
    ConverterFactory
    -0.68
    POSITIVE LOGITS
    <bos>
    1.98
     itſelf
    0.79
    ſelves
    0.63
     myſelf
    0.63
     Shakspeare
    0.62
     raiſ
    0.61
    )";
    0.60
     ſch
    0.60
     himſelf
    0.60
     Monfieur
    0.59
    Activations Density 0.591%

    No Known Activations