© 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. 54510
    Prev
    Next
    INDEX
    Explanations

    and

    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
     ጡ
    0.34
    怅
    0.34
     וש
    0.34
    諱
    0.34
     ਅਤੇ
    0.33
    广大
    0.32
    一个是
    0.31
    작
    0.31
     கருத
    0.31
    粎
    0.31
    POSITIVE LOGITS
    ैक्ट
    0.32
    Life
    0.32
     hablando
    0.32
    使其
    0.32
     Serikat
    0.31
    Men
    0.31
    ウィン
    0.31
     Bankers
    0.30
    ਈ
    0.30
    deserved
    0.30
    Activations Density 0.042%

    No Known Activations