© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62639
    Prev
    Next
    INDEX
    Explanations

    that's for sure

    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_11_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
    л
    0.62
    olig
    0.56
    з
    0.50
    érica
    0.49
     स्टेप
    0.49
    ल
    0.48
    ประกอบ
    0.47
    impi
    0.47
    <h3>
    0.46
    \
    0.46
    POSITIVE LOGITS
    的名
    0.63
    EY
    0.61
    ঁচ
    0.59
    的相关
    0.59
    IER
    0.57
    玧
    0.57
    চো
    0.57
    ето
    0.56
     pecans
    0.55
     thiab
    0.54
    Activations Density 0.000%

    No Known Activations