© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 121086
    Prev
    Next
    INDEX
    Explanations

    Bourbon Restoration

    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_37_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
     converting
    0.44
     প্রতির
    0.43
     coverage
    0.41
     extérieure
    0.38
    Converting
    0.38
    Pan
    0.37
    模
    0.37
     liners
    0.37
     coprodu
    0.37
    bust
    0.37
    POSITIVE LOGITS
     inactivació
    0.41
    গুপ্ত
    0.41
     abgeschlossen
    0.37
     shooter
    0.37
    OFFSET
    0.37
     Riggs
    0.36
    押
    0.36
    gou
    0.35
    掴
    0.35
     Reservations
    0.35
    Activations Density 0.002%

    No Known Activations