© 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. 213049
    Prev
    Next
    INDEX
    Explanations

    Paul

    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
    
    0.42
    timestamps
    0.40
    叨
    0.39
     harrow
    0.38
     pipette
    0.37
     Baran
    0.37
    वर्ड
    0.37
    setC
    0.36
    䘚
    0.35
    ovaní
    0.35
    POSITIVE LOGITS
     williams
    0.44
    pen
    0.39
     Williams
    0.38
    Pen
    0.38
    Williams
    0.38
    靖
    0.38
     kills
    0.37
    姆
    0.37
    ень
    0.36
    heben
    0.36
    Activations Density 0.001%

    No Known Activations