© 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. 5502
    Prev
    Next
    INDEX
    Explanations

    the word "clean" and its derivatives.

    oai_token-act-pair · gemini-2.0-flash

    instances of the word "clean"

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

    clean

    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
     Im
    -0.43
     Shed
    -0.42
     im
    -0.42
    awtextra
    -0.42
    іга
    -0.40
     Mammal
    -0.40
     kort
    -0.40
    вік
    -0.40
     Cal
    -0.40
    weli
    -0.39
    POSITIVE LOGITS
     مشين
    0.75
     EconPapers
    0.75
    NameInMap
    0.72
    WithIOException
    0.68
     Signalez
    0.67
     ویکی‌پدیای
    0.67
    __":
    0.66
    出版年
    0.66
    --)
    0.66
     AspNetCore
    0.65
    Activations Density 2.334%

    No Known Activations