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. 7-GEMMASCOPE-TRANSCODER-16K
    4. 6912
    Prev
    Next
    INDEX
    Explanations

    code snippets, version control terminology, and references to specific events or people associated with them.

    oai_token-act-pair · gemini-2.0-flash

    res

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    paksa
    -0.68
    Vidite
    -0.60
     ویکی‌پدیای
    -0.56
    pośred
    -0.55
    actéristique
    -0.54
     GenerationType
    -0.53
    éndole
    -0.52
     magasiner
    -0.51
    (:,
    -0.51
    éndolo
    -0.49
    POSITIVE LOGITS
    الإنجليزية
    0.69
    aarrggbb
    0.57
    
    0.51
    IsContent
    0.50
    LookAnd
    0.49
    เพ
    0.48
    thora
    0.47
    oredCriteria
    0.46
    verti
    0.46
    queryInterface
    0.46
    Activations Density 9.792%

    No Known Activations