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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1724
    Prev
    Next
    INDEX
    Explanations

    legal citations and terminology

    oai_token-act-pair · gemini-2.0-flash

    legal documents

    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
    iestety
    -0.73
     Efq
    -0.69
     againſt
    -0.69
    </h2>
    -0.67
    '])){
    
    -0.66
     crdi
    -0.62
    ''');
    -0.62
    .";
    
    -0.62
     Jefus
    -0.60
     pleaſure
    -0.60
    POSITIVE LOGITS
    nt
    0.65
    sen
    0.63
    ns
    0.62
    ’
    0.61
    nes
    0.60
    ms
    0.60
    med
    0.57
    ‘
    0.56
    ny
    0.56
    ng
    0.56
    Activations Density 9.106%

    No Known Activations