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. 6043
    Prev
    Next
    INDEX
    Explanations

    a specific set of terms. Likely names or abbreviations, and possibly some locations

    oai_token-act-pair · gemini-2.0-flash

    foreign language or brand names

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

    Anime robot descriptions

    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
    kste
    -0.45
     patch
    -0.45
     se
    -0.44
     Ku
    -0.44
    webElementXpaths
    -0.43
    ∇
    -0.43
     fald
    -0.43
     share
    -0.43
     part
    -0.42
     cre
    -0.42
    POSITIVE LOGITS
     يتيمه
    0.64
     itſelf
    0.64
     intercal
    0.61
     uniqlo
    0.60
    httphttps
    0.58
     irmã
    0.57
     iNdEx
    0.56
    hamdulillah
    0.56
     onCreateView
    0.56
     bershka
    0.56
    Activations Density 0.134%

    No Known Activations