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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 2298
    Prev
    Next
    INDEX
    Explanations

    words related to the internet, advertising, and content marketing

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/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
    itati
    -0.66
    iastes
    -0.64
    itative
    -0.62
    Portale
    -0.58
    ImageContext
    -0.56
    antry
    -0.54
    +/**
    -0.54
    itarian
    -0.53
     metav
    -0.53
    出版年
    -0.53
    POSITIVE LOGITS
     normaux
    0.53
     ainfi
    0.52
     feroit
    0.50
     المقال
    0.50
     bulundu
    0.48
     auroit
    0.48
     sauvages
    0.47
     longues
    0.47
    клопе
    0.47
     enfans
    0.46
    Activations Density 9.420%

    No Known Activations