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. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1012
    Prev
    Next
    INDEX
    Explanations

    discussions on education and teaching within school systems

    oai_token-act-pair · gemini-2.0-flash

    education, teachers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portail
    -0.63
    TargetException
    -0.57
     Roskov
    -0.56
     FontWeight
    -0.52
    loggen
    -0.51
     ویکی‌پدیا
    -0.50
     pof
    -0.49
    Portale
    -0.48
     مشين
    -0.47
    锈钢
    -0.46
    POSITIVE LOGITS
    حياته
    0.60
    AccessorTable
    0.56
    \{\\
    0.54
     الرياضيه
    0.54
    ViewFeatures
    0.52
    ThroughAttribute
    0.52
    makeConstraints
    0.52
     vostri
    0.51
    IntoConstraints
    0.50
     informée
    0.50
    Activations Density 27.628%

    No Known Activations