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. 15-GEMMASCOPE-TRANSCODER-16K
    4. 16228
    Prev
    Next
    INDEX
    Explanations

    words associated with systems, money, and medical issues

    oai_token-act-pair · gemini-2.0-flash

    finance and medicine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_15/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
    mybatisplus
    -0.73
    الإنجليزية
    -0.69
     désigne
    -0.53
    ContentAsync
    -0.53
    tomi
    -0.52
     škoda
    -0.50
    %
    
    -0.49
     = 
    -0.49
     protoimpl
    -0.49
     TREAS
    -0.49
    POSITIVE LOGITS
    tagHelperRunner
    0.61
    Conclusie
    0.55
    っこう
    0.52
     Cea
    0.52
    ciples
    0.52
    નું
    0.50
    GGLE
    0.49
     finalized
    0.49
    Conclusão
    0.49
    oniec
    0.48
    Activations Density 1.861%

    No Known Activations