© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 197964
    Prev
    Next
    INDEX
    Explanations

    fashion-forward

    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_12_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
    ice
    0.57
    ames
    0.52
    Cock
    0.52
    X
    0.52
    iesel
    0.51
    ann
    0.49
    aches
    0.49
    California
    0.49
    ulf
    0.49
    aces
    0.49
    POSITIVE LOGITS
    \
    0.48
     itinerant
    0.48
    стую
    0.47
    śla
    0.46
     contrário
    0.46
    setPreferred
    0.46
    र्तन
    0.45
    ுள்ளார்
    0.45
     Opposite
    0.44
     Qualquer
    0.44
    Activations Density 0.002%

    No Known Activations