© 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. 194956
    Prev
    Next
    INDEX
    Explanations

    depict

    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
    sid
    0.36
    ாடு
    0.36
    uvad
    0.36
    पीएससी
    0.36
    慥
    0.36
    éci
    0.35
     ඇ
    0.35
     อา
    0.35
    皖
    0.35
    rú
    0.34
    POSITIVE LOGITS
     Schloss
    0.42
     href
    0.39
     ching
    0.39
    工場
    0.39
     LCM
    0.38
    elems
    0.37
     jars
    0.37
     Mays
    0.37
    TER
    0.36
    ネル
    0.36
    Activations Density 0.006%

    No Known Activations