© 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. 30380
    Prev
    Next
    INDEX
    Explanations

    step by step instructions

    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
    ių
    0.54
    zers
    0.54
    ରି
    0.51
     hạ
    0.48
    ՜
    0.48
    ңү
    0.46
    тері
    0.45
    
    0.45
    িয়ায়
    0.45
    Founder
    0.45
    POSITIVE LOGITS
    breviations
    0.59
    ob
    0.53
    td
    0.52
    able
    0.50
    :
    0.50
    elabor
    0.49
    8
    0.47
     약
    0.47
    ework
    0.45
    ade
    0.45
    Activations Density 0.000%

    No Known Activations