© 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. 92068
    Prev
    Next
    INDEX
    Explanations

    HS code classification

    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
    is
    1.07
    ق
    0.98
    م
    0.89
    مون
    0.87
    ER
    0.86
    in
    0.79
    AR
    0.78
    ات
    0.78
    و
    0.75
    os
    0.73
    POSITIVE LOGITS
    </th>
    0.70
    </h3>
    0.66
     Blazer
    0.66
    я
    0.61
    示す
    0.58
    ΰ
    0.58
    itt
    0.57
    ール
    0.57
    ឡិច
    0.56
    </h5>
    0.55
    Activations Density 0.001%

    No Known Activations