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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 2337
    Prev
    Next
    INDEX
    Explanations

    CSS content related to styling objects/elements

    oai_token-act-pair · gemini-2.0-flash

    say "px"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/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
     uttered
    -0.52
     confiscation
    -0.48
    Considering
    -0.47
    Packed
    -0.46
    ونة
    -0.46
     scholastic
    -0.45
    出版年
    -0.44
     natale
    -0.44
     Schmer
    -0.44
     kuris
    -0.44
    POSITIVE LOGITS
     }}"></
    0.70
    stateProvider
    0.69
    ;';
    0.69
     endblock
    0.65
    ']))
    
    0.63
    }>;
    0.62
     }}">
    0.61
    %")
    0.60
    '){
    
    0.60
    ()]
    
    0.60
    Activations Density 5.603%

    No Known Activations