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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2968
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers, especially in relation to time or sports events

    oai_token-act-pair · gemini-2.0-flash

    technical or programming-related terms

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

    parts of a sequence

    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
     juſt
    -0.57
     firſt
    -0.57
     ſever
    -0.55
     Diſ
    -0.54
     diſt
    -0.54
     obſ
    -0.54
     laſt
    -0.54
     itſelf
    -0.53
     becauſe
    -0.52
     abſ
    -0.52
    POSITIVE LOGITS
    TagMode
    0.97
    MigrationBuilder
    0.75
    WebElementEntity
    0.69
    RegistryLite
    0.65
     חיצוניים
    0.65
    rungsseite
    0.64
     week
    0.63
    zzleHttp
    0.63
    UnknownFieldSet
    0.61
    IsContent
    0.60
    Activations Density 0.611%

    No Known Activations