© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54907
    Prev
    Next
    INDEX
    Explanations

    Japanese grammatical forms

    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_55_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
    라고
    0.42
    чан
    0.39
    uriken
    0.39
    ({});
    0.38
    etry
    0.38
    ayı
    0.38
     ؟
    0.38
    Ancient
    0.37
    geoip
    0.37
    amı
    0.37
    POSITIVE LOGITS
    はない
    0.38
     ಇ
    0.38
     penultimate
    0.37
    那位
    0.36
     এতটাই
    0.36
     none
    0.35
     kinship
    0.35
     unspoken
    0.35
    stuff
    0.35
    ल्हे
    0.35
    Activations Density 0.000%

    No Known Activations