© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 210284
    Prev
    Next
    INDEX
    Explanations

    speech recognition and completion

    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_10_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    櫚
    0.58
    ಾರೆ
    0.55
    in
    0.54
    参考
    0.52
    गन
    0.50
    자
    0.50
    갑
    0.49
    강
    0.49
    جة
    0.49
    सू
    0.47
    POSITIVE LOGITS
     zwycię
    0.64
     própri
    0.64
     зберіга
    0.63
     чувстви
    0.63
     جديد
    0.63
     deği
    0.62
     νέ
    0.62
    <unused693>
    0.62
     oraz
    0.61
     сохранить
    0.61
    Activations Density 0.030%

    No Known Activations