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. 15-GEMMASCOPE-TRANSCODER-16K
    4. 16245
    Prev
    Next
    INDEX
    Explanations

    mentions of multiple numbers

    oai_token-act-pair · gemini-2.0-flash

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_15/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
    InMillis
    -0.65
     decontamination
    -0.55
     metallurgy
    -0.55
     Mejía
    -0.54
     mía
    -0.53
     capacitance
    -0.53
     Observ
    -0.52
     serien
    -0.52
    ьаж
    -0.51
     pollination
    -0.51
    POSITIVE LOGITS
     autorytatywna
    0.79
     виправивши
    0.54
     BoxDecoration
    0.52
    msgTypes
    0.51
     تانيه
    0.51
    XmlAccessorType
    0.49
    QMetaType
    0.47
     الحره
    0.47
    enterOuterAlt
    0.45
    fjspx
    0.45
    Activations Density 0.974%

    No Known Activations