© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8742
    Prev
    Next
    INDEX
    Explanations

    Serena Dan East Side Gossip

    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_13_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
    că
    0.50
    ส์
    0.49
    ELEMENT
    0.48
    
    0.47
    ăr
    0.47
    Sf
    0.47
     antigua
    0.46
    КТ
    0.46
    EY
    0.45
    Rs
    0.45
    POSITIVE LOGITS
     inú
    0.50
    分數
    0.48
     Hubbard
    0.47
    道德
    0.47
    ศึกษา
    0.46
    బ్బ
    0.46
    紂
    0.46
     thermodynam
    0.45
     UP
    0.45
     ক্রস
    0.45
    Activations Density 0.000%

    No Known Activations