© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7586
    Prev
    Next
    INDEX
    Explanations

    sq mi

    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_39_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
     authentication
    0.30
     பார
    0.30
     hardware
    0.29
     trivial
    0.29
    硬件
    0.29
    嚕
    0.29
    穸
    0.28
     benchmark
    0.28
     ترا
    0.28
     wizards
    0.28
    POSITIVE LOGITS
    擘
    0.31
    ૢ
    0.30
    erer
    0.29
     नमस्ते
    0.29
     sacer
    0.28
    лость
    0.28
    plicht
    0.28
    แสง
    0.28
    KINS
    0.27
    owaniem
    0.27
    Activations Density 0.022%

    No Known Activations