© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7296
    Prev
    Next
    INDEX
    Explanations

    the word "one", often in the context of "one of a kind" or "one-"

    oai_token-act-pair · gemini-2.0-flash

    one

    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
    Negative Logits
    IntoConstraints
    -0.82
    drawSprites
    -0.72
    providedIn
    -0.71
     незавершена
    -0.71
    Hozzáférés
    -0.70
     StatefulWidget
    -0.68
    ^(@)
    -0.64
    RetentionPolicy
    -0.63
    Portale
    -0.62
     DriverManager
    -0.61
    POSITIVE LOGITS
     eight
    0.46
    CRIPT
    0.44
    ofa
    0.44
     zero
    0.43
    parsedMessage
    0.42
     forty
    0.42
     off
    0.41
     thirty
    0.40
     EIGHT
    0.40
     and
    0.40
    Activations Density 1.163%

    No Known Activations