© 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. 36979
    Prev
    Next
    INDEX
    Explanations

    yst

    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
    گا
    0.42
     фе
    0.41
    fea
    0.41
     skate
    0.40
     unresponsive
    0.40
    fek
    0.40
     berk
    0.39
    Enemy
    0.39
    lusconi
    0.39
     列
    0.39
    POSITIVE LOGITS
     dn
    0.41
    Studio
    0.38
    ocoder
    0.38
    kts
    0.38
     Voss
    0.36
    triangleright
    0.36
     Aydın
    0.36
     Studio
    0.35
     Artin
    0.35
     دوست
    0.34
    Activations Density 0.000%

    No Known Activations