© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 205472
    Prev
    Next
    INDEX
    Explanations

    endpoint server hostname

    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_20_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
    people
    0.50
    aver
    0.49
    tai
    0.49
     “[
    0.46
    intérieur
    0.45
    affin
    0.45
     fifteen
    0.45
     Sovereign
    0.45
    ouve
    0.45
     Rapt
    0.43
    POSITIVE LOGITS
    ни
    0.51
    EPEND
    0.48
    стно
    0.47
    లోని
    0.46
    겔
    0.45
     поро
    0.45
     &_
    0.45
    COVERY
    0.44
    цију
    0.44
    ਾਰ
    0.44
    Activations Density 0.001%

    No Known Activations