© 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. 205273
    Prev
    Next
    INDEX
    Explanations

    question marks

    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
    Negative Logits
     that
    1.13
    that
    1.00
    he
    0.89
     ਜੋ
    0.86
    at
    0.85
    ที่
    0.76
    K
    0.76
    ou
    0.75
     ਅਤੇ
    0.73
    ik
    0.73
    POSITIVE LOGITS
    관리
    0.64
    cción
    0.63
    дар
    0.63
    ější
    0.63
     کارڈ
    0.59
     رجل
    0.58
    ென்று
    0.58
    Puedes
    0.58
    </tr>
    0.57
    اسی
    0.57
    Activations Density 0.001%

    No Known Activations