© 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-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33302
    Prev
    Next
    INDEX
    Explanations

    dress code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    in
    0.93
    .
    0.93
    -
    0.72
    ρα
    0.71
    าร
    0.70
    า
    0.70
    at
    0.64
    อง
    0.64
    ON
    0.63
    人
    0.61
    POSITIVE LOGITS
     Vegetation
    0.64
    of
    0.63
    фик
    0.61
    崞
    0.61
    욌
    0.61
     Physica
    0.61
    ޏ
    0.60
    ፩
    0.59
    ዻ
    0.59
     Weierstrass
    0.59
    Activations Density 0.018%

    No Known Activations