© 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. 24041
    Prev
    Next
    INDEX
    Explanations

    bilateral

    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
    ために
    0.65
    ש
    0.59
     เดียว
    0.56
    Й
    0.55
    гие
    0.53
    РУ
    0.53
     codons
    0.53
     itineraries
    0.53
    routing
    0.52
    ма
    0.51
    POSITIVE LOGITS
    0.67
     I
    0.61
     дву
    0.57
     Hydro
    0.55
     THAT
    0.54
    (
    0.53
     Juven
    0.53
     Industri
    0.52
     can
    0.51
     Ferro
    0.51
    Activations Density 0.016%

    No Known Activations