© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 180121
    Prev
    Next
    INDEX
    Explanations

    Rai

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     الن
    0.40
    訣
    0.39
     confront
    0.38
     bes
    0.38
     siting
    0.38
     nouveau
    0.38
     sawa
    0.38
     clipping
    0.37
    鈷
    0.37
     १८४
    0.37
    POSITIVE LOGITS
     RAI
    0.51
     rai
    0.45
    doped
    0.42
    rai
    0.41
    emie
    0.40
    Zh
    0.39
     BRAD
    0.38
     Zeitschr
    0.38
     Rais
    0.38
     Rai
    0.38
    Activations Density 0.004%

    No Known Activations