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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 10178
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating value judgements and novel or original ideas

    oai_token-act-pair · gemini-2.0-flash

    sets and groupings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_19/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
     démocratie
    -0.54
    )";
    
    -0.50
    .";
    
    -0.50
    berdayakan
    -0.50
     ſeveral
    -0.47
    .")
    
    -0.46
     récents
    -0.46
     mourut
    -0.46
     Wicidata
    -0.45
     récente
    -0.44
    POSITIVE LOGITS
     and
    0.65
     number
    0.55
     piece
    0.54
     degree
    0.53
     combination
    0.53
     amount
    0.52
     set
    0.52
     list
    0.52
     situation
    0.52
     blend
    0.51
    Activations Density 7.255%

    No Known Activations