© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 207030
    Prev
    Next
    INDEX
    Explanations

    emojis related to people, healing, stars, and aids

    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_6_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
    s
    1.67
     in
    1.53
     في
    1.50
     در
    1.44
     в
    1.42
    ;
    1.41
     σε
    1.35
    k
    1.35
    在
    1.35
    e
    1.16
    POSITIVE LOGITS
    ang
    1.20
    ना
    0.99
    is
    0.81
    ো
    0.77
    ong
    0.77
    них
    0.75
    Nash
    0.74
     Printers
    0.73
    0.72
    lover
    0.71
    Activations Density 0.000%

    No Known Activations