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. 968
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to categorization, profiles, and external links, especially in the context of sports or biographical data

    oai_token-act-pair · gemini-2.0-flash

    at

    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
    AsUp
    -0.74
    AnchorTagHelper
    -0.65
    EndContext
    -0.64
    toupper
    -0.64
    expandindo
    -0.62
    ніципа
    -0.62
    istán
    -0.61
    makeText
    -0.59
     gepubliceerd
    -0.59
    +#+#
    -0.58
    POSITIVE LOGITS
    Pageable
    0.46
     gyhoeddwyd
    0.46
    AutoField
    0.43
    TProtocol
    0.43
    setScene
    0.43
    다는
    0.42
    垢
    0.42
    MigrationBuilder
    0.42
    ("-");
    0.41
    nend
    0.41
    Activations Density 0.747%

    No Known Activations