© 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. 212820
    Prev
    Next
    INDEX
    Explanations

    to

    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
    不一樣
    0.37
    FieldIndex
    0.37
    वीन
    0.36
     Оюн
    0.36
    明る
    0.36
     Noyes
    0.36
     नर्सिंग
    0.36
    monotonic
    0.36
    楠
    0.35
    मी
    0.35
    POSITIVE LOGITS
    хта
    0.43
    otas
    0.43
     tal
    0.43
     Swift
    0.43
    Swift
    0.42
     iP
    0.42
    tal
    0.40
     вя
    0.39
    cab
    0.38
    طل
    0.37
    Activations Density 0.001%

    No Known Activations