© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167925
    Prev
    Next
    INDEX
    Explanations

    graph structures or data definitions

    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_31_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
    ಹಿತ
    0.39
    廿
    0.36
     tag
    0.34
     Tag
    0.32
    อนุ
    0.32
    érios
    0.32
     algún
    0.31
     পৃথিবী
    0.31
    Гц
    0.30
     anthrac
    0.30
    POSITIVE LOGITS
    ="'$(
    0.36
    OY
    0.31
    ূর্ণ
    0.31
     נוס
    0.31
    READ
    0.30
     COURT
    0.30
    отно
    0.30
    ercase
    0.29
    クレ
    0.29
     Resolved
    0.29
    Activations Density 0.004%

    No Known Activations