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. 6036
    Prev
    Next
    INDEX
    Explanations

    LaTeX mathematical expressions.

    oai_token-act-pair · gemini-2.0-flash

    technical jargon related to programming or markup languages

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

    code and mathematical expressions

    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
     injunction
    -0.49
    ‌است
    -0.49
     Paglinawan
    -0.48
     CURIAM
    -0.46
    ائن
    -0.46
    webElement
    -0.46
    เช
    -0.45
    useEffect
    -0.45
    igslist
    -0.44
    cmath
    -0.44
    POSITIVE LOGITS
    esModule
    0.70
    ValueStyle
    0.62
     nahilalakip
    0.60
    AutoScale
    0.58
    UnknownFields
    0.57
    WriteTagHelper
    0.57
    tagHelperRunner
    0.56
    Cyfeiriadau
    0.56
    Chham
    0.55
    脚注の使い方
    0.55
    Activations Density 3.887%

    No Known Activations