© 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. 197838
    Prev
    Next
    INDEX
    Explanations

    arcade games and cabinets

    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
    0.61
     \
    0.55
    com
    0.51
    !
    0.50
    </
    0.48
    aduras
    0.46
    они
    0.46
    mathrm
    0.46
     They
    0.45
     Haha
    0.45
    POSITIVE LOGITS
    ﻲ
    0.54
     ټینس
    0.54
     restoran
    0.53
     tavern
    0.52
     казиносу
    0.52
    locationX
    0.49
     keli
    0.48
     tallest
    0.48
    餐廳
    0.48
    ISTS
    0.48
    Activations Density 0.000%

    No Known Activations