© 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. 179934
    Prev
    Next
    INDEX
    Explanations

    Lai

    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
     H
    0.60
     Joh
    0.52
     JOH
    0.50
     Johanna
    0.49
     joh
    0.48
     Hock
    0.48
    约翰
    0.45
     Johann
    0.45
     Johansson
    0.45
     Johnny
    0.44
    POSITIVE LOGITS
    ई
    0.41
    PTV
    0.41
    Пет
    0.40
    чён
    0.40
    隱
    0.39
    Ề
    0.39
    Galaxy
    0.39
    MaxWidth
    0.38
    Emily
    0.38
    BrN
    0.38
    Activations Density 0.012%

    No Known Activations