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. 11124
    Prev
    Next
    INDEX
    Explanations

    a broad array of common words and punctuation used to form sentences and questions.

    oai_token-act-pair · gemini-2.0-flash

    analytical processes

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

    analysis

    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
     يتيمه
    -0.55
    PMailer
    -0.44
     >=",
    -0.41
    XmlEnum
    -0.41
     menambah
    -0.40
    исленность
    -0.40
     lasciare
    -0.39
    tagena
    -0.39
     aggiungere
    -0.39
     Soporte
    -0.39
    POSITIVE LOGITS
     assessing
    1.46
     evaluating
    1.42
     examining
    1.41
     analyzing
    1.38
     analysing
    1.35
     investigating
    1.33
     checking
    1.30
     determining
    1.29
     discovering
    1.27
     looking
    1.25
    Activations Density 7.504%

    No Known Activations