© 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. 113196
    Prev
    Next
    INDEX
    Explanations

    trattoria

    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
    Not in Any Lists

    No Comments

    Negative Logits
    س
    2.00
    는
    1.46
    с
    1.41
    ा
    1.41
    وا
    1.40
    ا
    1.34
    ی
    1.32
    نا
    1.30
    માં
    1.30
    다
    1.30
    POSITIVE LOGITS
    Y
    1.30
    z
    1.07
    ,
    1.00
    st
    0.95
     κά
    0.88
    hna
    0.88
    AND
    0.83
    \},
    0.81
     современ
    0.79
    inin
    0.79
    Activations Density 0.001%

    No Known Activations