© 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. 41304
    Prev
    Next
    INDEX
    Explanations

    overlay networking and functionality

    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
     asigur
    0.55
     加入
    0.55
     ém
    0.54
     azimuthal
    0.54
     saddhim
    0.54
     organiza
    0.52
     thóc
    0.52
     movilidad
    0.51
    тта
    0.51
    🤟
    0.51
    POSITIVE LOGITS
    D
    0.71
     D
    0.61
    H
    0.61
    C
    0.58
    V
    0.58
     you
    0.58
     be
    0.57
    public
    0.55
     R
    0.55
     V
    0.53
    Activations Density 0.001%

    No Known Activations