© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 77507
    Prev
    Next
    INDEX
    Explanations

    transliteration and special characters

    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_29_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
    ảo
    0.45
    των
    0.38
    France
    0.37
    ámara
    0.37
    ſed
    0.37
    iodo
    0.36
     ۔
    0.36
    aband
    0.36
    σωπ
    0.36
    ান্ডার
    0.35
    POSITIVE LOGITS
     LaTeX
    0.40
     create
    0.38
     breach
    0.37
    ᱓
    0.37
     जन्
    0.37
     estimating
    0.37
     सटीक
    0.36
     CGRectMake
    0.36
     निर
    0.36
     ADHD
    0.35
    Activations Density 0.010%

    No Known Activations