© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14013
    Prev
    Next
    INDEX
    Explanations

    text describing or promoting books.

    oai_token-act-pair · gemini-2.0-flash

    book descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     typelib
    -0.70
    RectangleBorder
    -0.65
     HasFactory
    -0.62
    dotenv
    -0.59
    šanai
    -0.57
    cheibe
    -0.56
     gerek
    -0.56
     LUMP
    -0.55
    isfile
    -0.54
     segreto
    -0.54
    POSITIVE LOGITS
    chende
    0.54
     handy
    0.53
     reproducible
    0.52
    ifferentiated
    0.49
     ligiloj
    0.49
     useful
    0.49
    Примечания
    0.48
    BeginContext
    0.47
     bite
    0.47
     short
    0.46
    Activations Density 2.720%

    No Known Activations