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. 11099
    Prev
    Next
    INDEX
    Explanations

    the names of organizations and places, especially those in Texas

    oai_token-act-pair · gemini-2.0-flash

    technical terms and jargon

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

    Dallas

    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
     Maß
    -0.41
    amarin
    -0.41
     effective
    -0.41
     Incentive
    -0.40
    Ine
    -0.39
     tuyến
    -0.38
     Gaines
    -0.37
     forces
    -0.37
     Forces
    -0.37
    нача
    -0.37
    POSITIVE LOGITS
     للاسماء
    0.86
     الحره
    0.84
    MemoryWarning
    0.82
    DoubleQuotes
    0.74
    \{\\
    0.70
    Hentet
    0.69
    sizeCache
    0.68
    SharedDtor
    0.68
     متعلقه
    0.65
     parseFrom
    0.65
    Activations Density 0.772%

    No Known Activations