© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5629
    Prev
    Next
    INDEX
    Explanations

    the different roles or positions a person holds, like singer, actor, member of a group, or head of radio

    oai_token-act-pair · gemini-2.0-flash

    multi-language keywords or specific terms

    np_token-act-pair-logits · gpt-4o-mini

    Locations and places

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    withstanding
    -0.61
     Rhea
    -0.56
     Borel
    -0.55
     minimization
    -0.55
     față
    -0.54
     hilt
    -0.53
     myeloma
    -0.53
     Monfieur
    -0.53
     dreamstime
    -0.52
     Theſe
    -0.52
    POSITIVE LOGITS
    GEBURTSDATUM
    0.68
    expandindo
    0.59
    الحياه
    0.57
     resourceCulture
    0.57
    OGND
    0.56
    MigrationBuilder
    0.53
     שוליים
    0.52
    Билгалдахарш
    0.49
    Nazionale
    0.49
    enumi
    0.48
    Activations Density 1.705%

    No Known Activations