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. 5919
    Prev
    Next
    INDEX
    Explanations

    text giving instructions or advice about personal habits, routines, and choices

    oai_token-act-pair · gemini-2.0-flash

    programming and technical terms

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

    Random text 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
     superiori
    -0.61
     supérieurs
    -0.57
     legale
    -0.56
     légal
    -0.56
     romantique
    -0.55
     dieux
    -0.55
     gouver
    -0.55
     بيها
    -0.53
     fuite
    -0.52
     subterrá
    -0.52
    POSITIVE LOGITS
     estekak
    0.72
     AssemblyTitle
    0.68
    DockStyle
    0.68
     <<<<<<<<<<<<<<
    0.67
    脚注の使い方
    0.60
    TypedDataSet
    0.59
     يتيمه
    0.59
     crossorigin
    0.58
     set
    0.57
    клопе
    0.57
    Activations Density 1.788%

    No Known Activations