© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13957
    Prev
    Next
    INDEX
    Explanations

    the word "reveal" or its synonyms

    oai_token-act-pair · gemini-2.0-flash

    reveal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    awtextra
    -1.09
    WriteLiteral
    -0.78
    存于互联网档案馆
    -0.75
    WithMany
    -0.70
     reveal
    -0.67
    </blockquote>
    -0.67
    CPtr
    -0.66
    __*/
    -0.63
     fla
    -0.61
     –
    -0.61
    POSITIVE LOGITS
     avoient
    1.13
     myſelf
    1.10
     étoit
    1.10
     auroit
    1.09
     itſelf
    1.08
     feroit
    1.07
     pouvoit
    1.03
     avoit
    1.02
     étoient
    1.00
     purpoſe
    1.00
    Activations Density 1.206%

    No Known Activations