© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 226732
    Prev
    Next
    INDEX
    Explanations

    awards

    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_10_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
    ру
    0.52
    ા
    0.48
    ارع
    0.47
    <0x98>
    0.47
    ání
    0.47
    туру
    0.46
     Verhalten
    0.46
     molécules
    0.46
    ндо
    0.45
    ياء
    0.44
    POSITIVE LOGITS
    k
    0.54
     anv
    0.52
     novo
    0.52
     riun
    0.51
     on
    0.50
     has
    0.50
     nor
    0.49
     hava
    0.49
     tree
    0.49
     falls
    0.49
    Activations Density 0.000%

    No Known Activations