© 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. 179755
    Prev
    Next
    INDEX
    Explanations

    Haute

    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
    Not in Any Lists

    No Comments

    Negative Logits
    िशन
    0.45
     holo
    0.44
     Bi
    0.43
     biotin
    0.41
     HN
    0.41
    ón
    0.39
     H
    0.39
     Diaries
    0.38
     Homer
    0.38
     ஹை
    0.38
    POSITIVE LOGITS
    מצע
    0.43
    ZU
    0.40
     nests
    0.38
    heer
    0.38
    heard
    0.38
     उपाध्याय
    0.37
    巣
    0.37
    gar
    0.37
    Castro
    0.36
    hir
    0.35
    Activations Density 0.000%

    No Known Activations