© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35015
    Prev
    Next
    INDEX
    Explanations

    Japanese particles and verb 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_11_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
    ו
    0.31
     erken
    0.30
     değer
    0.29
    ק
    0.29
     Interestingly
    0.28
    İZ
    0.27
    ש
    0.26
     deniz
    0.26
     materially
    0.25
     但是
    0.25
    POSITIVE LOGITS
     Equitable
    0.30
     Polynomial
    0.30
     Chloride
    0.29
     Arch
    0.29
     Spreadsheet
    0.29
     want
    0.28
     cropped
    0.28
    ’
    0.28
    mont
    0.27
     Rapport
    0.27
    Activations Density 0.001%

    No Known Activations