© 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. 180018
    Prev
    Next
    INDEX
    Explanations

    names international words

    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
    谢
    0.45
     Tracking
    0.40
     Simulation
    0.39
     Pumps
    0.39
    ayım
    0.39
    mey
    0.38
    Pump
    0.38
    Simulation
    0.38
     Mutations
    0.38
    謝
    0.38
    POSITIVE LOGITS
    жні
    0.40
    Maria
    0.40
    NIA
    0.40
    scored
    0.39
     ありがとう
    0.39
    니아
    0.39
    ียน
    0.38
    ضور
    0.38
    maria
    0.37
     добро
    0.36
    Activations Density 0.000%

    No Known Activations