© 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. 40502
    Prev
    Next
    INDEX
    Explanations

    regions

    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
    ون
    0.79
    ونها
    0.66
    that
    0.66
    kenalkan
    0.63
    t
    0.63
     внед
    0.61
    c
    0.59
    us
    0.58
    -
    0.57
    வாய்
    0.56
    POSITIVE LOGITS
     are
    0.64
     কিন্ত
    0.63
    ﺘ
    0.61
    на
    0.60
     था
    0.59
    না
    0.58
    ၏
    0.58
    জ
    0.58
    ﺨ
    0.57
     Houghton
    0.57
    Activations Density 0.000%

    No Known Activations