© 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. 47155
    Prev
    Next
    INDEX
    Explanations

    M&A and business activities

    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
    ิ
    0.83
    '
    0.73
    i
    0.71
    い
    0.66
    ი
    0.63
     limpi
    0.63
    ी
    0.63
    ி
    0.63
    า
    0.63
    ant
    0.62
    POSITIVE LOGITS
     \
    0.73
     heeft
    0.68
    gène
    0.68
    দের
    0.67
     avez
    0.64
    t
    0.64
    Have
    0.63
     anderer
    0.63
    $}
    0.61
    يه
    0.61
    Activations Density 0.001%

    No Known Activations