Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5969
    Prev
    Next
    INDEX
    Explanations

    text from blog posts about crafting, specifically cardmaking

    oai_token-act-pair · gemini-2.0-flash

    nonsensical or unusual tokens

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

    punctuation

    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
    UnusedPrivate
    -0.53
     Normdatei
    -0.50
     --;
    -0.49
     linkovi
    -0.48
    ابق
    -0.48
    ButterKnife
    -0.48
    Referencer
    -0.46
     مقد
    -0.45
    LayoutStyle
    -0.44
     communs
    -0.44
    POSITIVE LOGITS
    $_['
    0.60
    RenderAtEndOf
    0.60
    Espèce
    0.59
     stork
    0.58
     pinulongan
    0.58
    >{@
    0.57
    unhofer
    0.56
     reckoned
    0.56
     мәкал
    0.56
     Baillargeon
    0.55
    Activations Density 1.757%

    No Known Activations