© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 88703
    Prev
    Next
    INDEX
    Explanations

    hexadecimal representation of text

    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_11_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
    Ob
    0.60
    ltre
    0.60
    P
    0.55
    Na
    0.55
    ാവ
    0.54
    ''''
    0.54
    ostino
    0.54
    ()'
    0.53
    s
    0.53
    rsquo
    0.53
    POSITIVE LOGITS
     THESE
    0.68
     запол
    0.61
    :
    0.59
     SCHOOL
    0.55
     haga
    0.55
    ট
    0.55
     помещение
    0.55
    то
    0.54
     этот
    0.54
     tingkat
    0.54
    Activations Density 0.000%

    No Known Activations