© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 87475
    Prev
    Next
    INDEX
    Explanations

    say =

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    =
    0.69
     x
    0.63
    .(
    0.57
    ((
    0.55
     =(
    0.55
     >
    0.55
     ==
    0.54
    =(
    0.53
    =((
    0.51
    (
    0.51
    POSITIVE LOGITS
     रंग
    0.55
     رنگ
    0.54
     컬러
    0.50
     색
    0.49
     colorido
    0.48
     color
    0.48
     المجموعة
    0.48
     COLOR
    0.48
     カラー
    0.48
     समूह
    0.48
    Activations Density 0.020%

    No Known Activations