© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10221
    Prev
    Next
    INDEX
    Explanations

    words related to travel, especially including cruises and travel accessories

    oai_token-act-pair · gemini-2.0-flash

    appliance-related terms

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

    comfort and amenities

    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
    पया
    -0.60
     Handle
    -0.59
    handle
    -0.59
    Rohy
    -0.57
    embatan
    -0.56
    TypedDataSet
    -0.56
    Gön
    -0.56
    nastics
    -0.55
    corer
    -0.55
    anterie
    -0.54
    POSITIVE LOGITS
    AsUp
    0.54
     washer
    0.52
     TV
    0.48
     ironing
    0.48
     dressing
    0.48
     tv
    0.48
    Архівовано
    0.47
     trái
    0.47
     washers
    0.46
     Washer
    0.46
    Activations Density 1.066%

    No Known Activations