© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 113302
    Prev
    Next
    INDEX
    Explanations

    Russian suffixes and 'kh' sounds

    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_2_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
    ש
    1.34
    ล
    1.30
    ف
    1.28
    ת
    1.24
    ي
    1.22
    ম
    1.21
    म
    1.13
    ו
    1.13
    ل
    1.12
    장
    1.05
    POSITIVE LOGITS
     that
    1.40
    LO
    1.04
     be
    0.97
    that
    0.96
    :
    0.96
    ill
    0.95
    il
    0.95
    int
    0.92
    DE
    0.92
    ach
    0.90
    Activations Density 0.000%

    No Known Activations