© 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. 39926
    Prev
    Next
    INDEX
    Explanations

    body positive systems

    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
     différences
    0.69
     thug
    0.57
    Yesterday
    0.55
    {$
    0.55
    𝗗
    0.54
    Differences
    0.54
    એ
    0.54
    ır
    0.53
     diferenças
    0.52
    まあ
    0.51
    POSITIVE LOGITS
    </h4>
    0.84
    </h2>
    0.79
    ات
    0.77
    ↵
    0.73
    ца
    0.70
    </h1>
    0.66
    ")){
    0.66
     Eid
    0.66
    ز
    0.65
    त
    0.64
    Activations Density 0.003%

    No Known Activations