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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14020
    Prev
    Next
    INDEX
    Explanations

    words describing people doing something or the description of something changing

    oai_token-act-pair · gemini-2.0-flash

    technical/code language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/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
     Theſe
    -0.82
    ſelf
    -0.77
     Jefus
    -0.71
     Monfieur
    -0.71
     pleaſure
    -0.70
     ſche
    -0.69
     Houſe
    -0.69
     Beſ
    -0.68
     houſe
    -0.68
     unſ
    -0.66
    POSITIVE LOGITS
    RenderAtEndOf
    0.64
     propOrder
    0.62
    EndContext
    0.51
    //
    0.49
    RuleContext
    0.47
     "..\..\..\
    0.47
    yntaxException
    0.44
    bkz
    0.44
    :✨
    0.43
    کتور
    0.41
    Activations Density 8.938%

    No Known Activations