© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136244
    Prev
    Next
    INDEX
    Explanations

    film, web, spools, tape, splicing

    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_12_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
    st
    0.51
    li
    0.51
    particles
    0.50
    inkl
    0.50
    لق
    0.50
    ли
    0.49
    ui
    0.47
    لی
    0.47
    ո
    0.46
    populations
    0.46
    POSITIVE LOGITS
     ткани
    0.57
     стр
    0.54
     nebude
    0.52
    стр
    0.51
    }_{
    0.50
     sarà
    0.49
     sera
    0.49
     ткань
    0.48
     будет
    0.48
     Чем
    0.48
    Activations Density 0.001%

    No Known Activations