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. 5917
    Prev
    Next
    INDEX
    Explanations

    code, XML, and programming syntax and structures

    oai_token-act-pair · gemini-2.0-flash

    specialized formatting or markup patterns

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

    Code/markup

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.56
    ,
    -0.54
     mit
    -0.54
     
    -0.53
     «
    -0.52
    :
    -0.51
     Mac
    -0.50
    ).
    -0.49
    ),
    -0.48
    ?
    -0.48
    POSITIVE LOGITS
     itſelf
    0.98
    ſelves
    0.98
    ſelf
    0.91
    ScopeManager
    0.88
     Majefty
    0.84
     ་་
    0.84
     Diſ
    0.83
    !")
    
    0.79
     שוליים
    0.79
    ValueStyle
    0.78
    Activations Density 6.771%

    No Known Activations