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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5105
    Prev
    Next
    INDEX
    Explanations

    numbers, symbols, and various formatting elements in different contexts like measurements, percentages, coordinates, or diagram labels.

    oai_token-act-pair · gemini-2.0-flash

    technical and programming terms

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

    numbers

    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
     متعلقه
    -0.78
    
    -0.73
     AssemblyProduct
    -0.70
     Majefty
    -0.69
    IsContent
    -0.69
    UnitTesting
    -0.68
    RenderAtEndOf
    -0.66
     lenker
    -0.66
    orghe
    -0.65
    ſelf
    -0.65
    POSITIVE LOGITS
    ToAction
    0.50
    thenes
    0.47
    awtextra
    0.46
     <>",
    0.40
    шил
    0.40
    wies
    0.39
    İstinadlar
    0.39
    тельстве
    0.39
    InjectAttribute
    0.38
    tama
    0.38
    Activations Density 8.606%

    No Known Activations