© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33603
    Prev
    Next
    INDEX
    Explanations

    software library names

    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_40_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
     viso
    0.47
     vis
    0.47
     equiv
    0.45
    vis
    0.45
     visor
    0.43
    avi
    0.42
    Vis
    0.42
    விக்கும்
    0.41
    鞆
    0.39
    avis
    0.39
    POSITIVE LOGITS
    を含
    0.37
    ྭ
    0.35
     contains
    0.35
    ミング
    0.34
     Claus
    0.34
     Shed
    0.33
    増加
    0.33
     newInput
    0.33
     Hall
    0.33
     hall
    0.33
    Activations Density 0.006%

    No Known Activations