© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156329
    Prev
    Next
    INDEX
    Explanations

    name beginnings like Doris

    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_2_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
    <0x0D>
    1.68
    ل
    1.67
    на
    1.54
    </h2>
    1.41
    し
    1.39
    ä
    1.37
    在
    1.27
     an
    1.25
    ne
    1.23
    im
    1.19
    POSITIVE LOGITS
    지
    1.33
    is
    1.23
    db
    1.16
    ють
    1.13
    daten
    1.12
    ский
    0.99
    지와
    0.99
    den
    0.99
    ます
    0.97
    does
    0.96
    Activations Density 0.000%

    No Known Activations