© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30500
    Prev
    Next
    INDEX
    Explanations

    zog

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
     Budget
    0.39
    纸
    0.37
    缕
    0.37
    绡
    0.37
     careful
    0.36
     гало
    0.35
     intentional
    0.35
     Magde
    0.35
     紙
    0.35
    骏
    0.35
    POSITIVE LOGITS
     நினைக்க
    0.39
     drills
    0.38
    ורי
    0.37
     outing
    0.36
    Elev
    0.36
     toll
    0.35
    賠
    0.35
    xan
    0.34
     ખે
    0.34
    רו
    0.34
    Activations Density 0.002%

    No Known Activations