© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 141645
    Prev
    Next
    INDEX
    Explanations

    likely followed by a descriptor

    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_0_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
     for
    2.13
    .
    1.61
    UT
    1.60
    for
    1.48
    س
    1.46
     it
    1.38
    ется
    1.36
     the
    1.35
    ن
    1.31
     that
    1.29
    POSITIVE LOGITS
    '
    1.66
    ים
    1.48
     و
    1.43
    u
    1.40
    是
    1.40
    ς
    1.38
    ックス
    1.30
     Фран
    1.27
    ی
    1.18
    는
    1.16
    Activations Density 0.002%

    No Known Activations