© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12394
    Prev
    Next
    INDEX
    Explanations

    code syntax: parentheses and certain operators

    oai_token-act-pair · gemini-2.0-flash

    code assignments and initializations

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

    Code

    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
    contentLoaded
    -0.59
     $=$
    -0.51
    Diweddarwch
    -0.48
    =
    -0.48
    []{"
    -0.47
    WindowConstants
    -0.47
    тех
    -0.47
     ExecuteAsync
    -0.46
    жере
    -0.45
    Since
    -0.45
    POSITIVE LOGITS
     InputDecoration
    0.70
    principalTable
    0.59
     BoxDecoration
    0.59
    تفصیلات
    0.58
    findpost
    0.58
    disposing
    0.56
    RAINT
    0.56
    hilangan
    0.54
    TextSpan
    0.53
    keyColumn
    0.52
    Activations Density 0.736%

    No Known Activations