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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16301
    Prev
    Next
    INDEX
    Explanations

    code snippets and related keywords like transaction and commit

    oai_token-act-pair · gemini-2.0-flash

    transaction operations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/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
    InjectAttribute
    -0.63
    Portale
    -0.62
     doInBackground
    -0.60
    Portail
    -0.59
    بوابة
    -0.57
     Accesat
    -0.57
    mybatisplus
    -0.56
    riebene
    -0.56
    Abitanti
    -0.56
     архивлан
    -0.54
    POSITIVE LOGITS
     try
    0.88
     transaction
    0.80
    try
    0.79
    Transaction
    0.73
     Transaction
    0.73
     catch
    0.71
     transactions
    0.71
    catch
    0.70
     Try
    0.68
    Try
    0.67
    Activations Density 2.240%

    No Known Activations