© 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. 214950
    Prev
    Next
    INDEX
    Explanations

    freeze leftovers

    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
    Negative Logits
    竈
    0.45
     శా
    0.38
     <*>
    0.38
    
    0.37
    BleStatus
    0.35
    Perm
    0.34
     Perm
    0.34
     キャ
    0.34
     اسٹ
    0.34
    畄
    0.34
    POSITIVE LOGITS
     Bauern
    0.42
     బంగారం
    0.39
     Returns
    0.39
    úde
    0.38
    ilded
    0.38
     gór
    0.36
     घोटा
    0.35
     returns
    0.35
     farmers
    0.34
    Returns
    0.34
    Activations Density 0.002%

    No Known Activations