© 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. 47212
    Prev
    Next
    INDEX
    Explanations

    Hero

    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
    t
    0.92
    z
    0.77
    g
    0.75
    v
    0.74
    í
    0.74
    u
    0.73
    ı
    0.73
    ut
    0.71
    d
    0.68
    ó
    0.64
    POSITIVE LOGITS
     tłumac
    0.70
     publicaciones
    0.66
     தெரிவித்தனர்
    0.60
     इस्तेमाल
    0.59
     encrypt
    0.57
     ĝi
    0.57
     공식
    0.57
     καθώς
    0.57
     kasut
    0.56
    つ
    0.56
    Activations Density 0.003%

    No Known Activations