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. 5860
    Prev
    Next
    INDEX
    Explanations

    javascript code snippets, especially those related to UI events like onclick

    oai_token-act-pair · gemini-2.0-flash

    programming function names or handlers

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

    Code snippets

    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
    ViewFeatures
    -0.69
    deelte
    -0.63
     AHEAD
    -0.54
     spéciales
    -0.50
     spéciaux
    -0.50
     quoique
    -0.50
     Ahead
    -0.50
    Bedankt
    -0.50
     obligé
    -0.49
     ordinaires
    -0.49
    POSITIVE LOGITS
    Rhestr
    0.55
    errHandler
    0.53
    apnews
    0.52
    makeConstraints
    0.51
    èdia
    0.50
    ConstraintMaker
    0.50
     sho
    0.49
     respeito
    0.48
    TestMethod
    0.47
    TemporalType
    0.47
    Activations Density 1.096%

    No Known Activations