© 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. 154271
    Prev
    Next
    INDEX
    Explanations

    Python type hints

    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
     siting
    0.45
     Bead
    0.39
     bead
    0.38
     guardianship
    0.38
     excre
    0.38
     beads
    0.37
    咾
    0.37
     Karen
    0.37
    फै
    0.37
     Cables
    0.37
    POSITIVE LOGITS
    奈
    0.38
     st
    0.37
    UL
    0.37
     packed
    0.37
    ដ្ឋ
    0.37
     тип
    0.37
    GG
    0.37
    packed
    0.37
    ague
    0.36
     type
    0.36
    Activations Density 0.000%

    No Known Activations