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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 2325
    Prev
    Next
    INDEX
    Explanations

    hyphenated words and website- or tech-related words

    oai_token-act-pair · gemini-2.0-flash

    hyphen

    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
    مصادر
    -0.39
    <bos>
    -0.39
     mallorca
    -0.32
     MediaType
    -0.31
     HomeScreen
    -0.31
    Viitteet
    -0.30
     domestiques
    -0.30
     Angele
    -0.30
    Portail
    -0.30
     stad
    -0.30
    POSITIVE LOGITS
    hematical
    0.73
     which
    0.73
     the
    0.72
     not
    0.71
     no
    0.71
     how
    0.70
     why
    0.70
     it
    0.70
     or
    0.70
     what
    0.70
    Activations Density 32.051%

    No Known Activations