© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 134223
    Prev
    Next
    INDEX
    Explanations

    cooking verbs

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     Kuk
    0.44
     kuk
    0.44
    くい
    0.43
     coco
    0.43
     кое
    0.42
     쿠
    0.41
     কো
    0.41
    kuk
    0.41
    Coco
    0.41
    Kö
    0.40
    POSITIVE LOGITS
     memas
    0.80
     طب
    0.69
    طب
    0.54
     μα
    0.53
     پک
    0.52
    Mas
    0.51
    mas
    0.50
     ச
    0.50
     Mas
    0.49
     fő
    0.49
    Activations Density 0.000%

    No Known Activations