© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 45191
    Prev
    Next
    INDEX
    Explanations

    consonants, suffixes, and multi-lingual endings

    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_10_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
    ल
    0.31
    म
    0.25
     अच्छे
    0.24
     अच्छी
    0.23
    л
    0.23
    ق
    0.23
    okkh
    0.22
     Representatives
    0.21
    ;
    0.21
    Während
    0.21
    POSITIVE LOGITS
    ar
    0.30
    asim
    0.22
    arono
    0.21
    ีด
    0.20
     grantor
    0.20
    alet
    0.20
     spune
    0.20
    ेलर
    0.20
    ار
    0.20
     pea
    0.20
    Activations Density 0.004%

    No Known Activations