© 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. 30850
    Prev
    Next
    INDEX
    Explanations

    V, VP

    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
     ges
    0.38
     Stiles
    0.37
     pube
    0.36
     Hays
    0.36
     Niles
    0.36
    슭
    0.36
     stalk
    0.35
    abay
    0.35
     Gases
    0.35
     гене
    0.34
    POSITIVE LOGITS
     V
    0.64
    V
    0.57
     v
    0.55
    v
    0.51
    Resol
    0.47
    VP
    0.44
    Catal
    0.44
    Touch
    0.43
     ката
    0.43
     Touch
    0.42
    Activations Density 0.022%

    No Known Activations