© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40543
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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_3_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
    ン
    0.77
    ال
    0.71
    Ident
    0.70
    UC
    0.70
    न
    0.68
    t
    0.68
    ET
    0.66
    א
    0.64
    ّ
    0.64
    is
    0.63
    POSITIVE LOGITS
    h
    0.89
     capacitance
    0.64
    گونه
    0.61
    ็ค
    0.59
     contoured
    0.57
    accoon
    0.55
    скольку
    0.54
    รง
    0.54
     trigonometry
    0.53
     були
    0.53
    Activations Density 0.006%

    No Known Activations