© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 145594
    Prev
    Next
    INDEX
    Explanations

    foreign sounds

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     T
    2.95
     الت
    1.98
    T
    1.70
     Т
    1.59
     הט
    1.28
    Ｔ
    1.20
     टी
    1.15
     Τ
    1.07
    𝑇
    1.04
     ट
    0.97
    POSITIVE LOGITS
    泰
    0.46
     টা
    0.45
     താ
    0.42
     التأ
    0.42
     টাই
    0.41
     Tiger
    0.41
    Tap
    0.41
    Ti
    0.41
     Tap
    0.41
    タイ
    0.41
    Activations Density 0.003%

    No Known Activations