© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 74662
    Prev
    Next
    INDEX
    Explanations

    high importance

    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_31_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
     softer
    0.42
     $(<
    0.39
     $<
    0.39
     toothbrush
    0.38
     ㅏ
    0.37
    imeric
    0.37
     ADAM
    0.36
     soft
    0.35
    Trich
    0.35
     fleshy
    0.35
    POSITIVE LOGITS
    澳門
    0.38
     coll
    0.35
    nika
    0.35
     существо
    0.35
     downsides
    0.35
     approach
    0.35
    asını
    0.34
    禊
    0.34
     નિર્
    0.33
     պատ
    0.33
    Activations Density 0.012%

    No Known Activations