© 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. 85417
    Prev
    Next
    INDEX
    Explanations

    alleviating

    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
     gå
    0.65
    ре
    0.63
    ли
    0.63
    ne
    0.62
     없다
    0.61
     tän
    0.59
    sville
    0.59
     ."
    0.59
     बलात्कार
    0.58
    </h2>
    0.57
    POSITIVE LOGITS
    та
    0.93
    ما
    0.84
    á
    0.83
    {
    0.77
    ය
    0.73
    이
    0.72
    అ
    0.71
    스와
    0.71
    ี
    0.70
     be
    0.70
    Activations Density 0.001%

    No Known Activations