Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11186
    Prev
    Next
    INDEX
    Explanations

    source code formatting and syntax, specifically looking for indentation and patterns in various programming languages

    oai_token-act-pair · gemini-2.0-flash

    JSON-like structures

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

    curly brace

    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
     GenerationType
    -0.95
     auffi
    -0.94
     FetchType
    -0.85
    ]--;
    -0.85
    aarrggbb
    -0.82
     Jefus
    -0.82
     للمعارف
    -0.82
     wikipagina
    -0.82
     ModelExpression
    -0.81
     ainfi
    -0.81
    POSITIVE LOGITS
     {
    0.90
    {
    0.78
     {}
    0.59
    {~
    0.57
    {}
    0.56
     {'
    0.56
    >{
    0.55
     {?
    0.53
     {(
    0.53
    nting
    0.53
    Activations Density 0.807%

    No Known Activations