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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 13622
    Prev
    Next
    INDEX
    Explanations

    mentions of international organizations

    oai_token-act-pair · gemini-2.0-flash

    Nations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    Nation
    -0.43
     privadas
    -0.40
     interacts
    -0.38
    enterio
    -0.38
     deportivas
    -0.38
    强的
    -0.38
    ('/:
    -0.38
     Nation
    -0.38
     Nations
    -0.37
    deleteById
    -0.36
    POSITIVE LOGITS
    migrationBuilder
    0.83
    Tembelea
    0.83
    bootstrapcdn
    0.81
    ########.
    0.80
    URLException
    0.78
    Искәрмәләр
    0.77
     Normdatei
    0.76
    TagMode
    0.74
    Datuak
    0.73
    $_['
    0.73
    Activations Density 0.184%

    No Known Activations