© 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. 48102
    Prev
    Next
    INDEX
    Explanations

    拉, 拖, 撕 (pull, drag, tear)

    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
     mysteriously
    0.43
    谜
    0.38
     휴
    0.37
    intah
    0.36
     हि
    0.36
    鹉
    0.36
    精灵
    0.36
     अज्ञात
    0.35
     mysterious
    0.35
     mysteries
    0.35
    POSITIVE LOGITS
    irrah
    0.37
    illumin
    0.37
    癲
    0.36
     vineyard
    0.36
    いている
    0.36
    マガ
    0.35
     increment
    0.35
     Somerset
    0.35
     viz
    0.35
     (%
    0.35
    Activations Density 0.001%

    No Known Activations