© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91922
    Prev
    Next
    INDEX
    Explanations

    would like to or would not

    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_3_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
    د
    0.99
    a
    0.96
    .
    0.82
    ه
    0.82
    س
    0.74
    in
    0.72
    在
    0.71
    o
    0.70
     in
    0.70
    ని
    0.66
    POSITIVE LOGITS
    ы
    0.74
    າວ
    0.71
    ъ
    0.71
    ë
    0.68
    о
    0.66
    ี
    0.63
    ິ
    0.62
    ן
    0.61
    ō
    0.61
    Ấ
    0.61
    Activations Density 0.001%

    No Known Activations