© 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. 121671
    Prev
    Next
    INDEX
    Explanations

    enchantments

    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
    antin
    0.76
    </h3>
    0.65
    大规模
    0.65
    ας
    0.64
    ors
    0.63
    alk
    0.62
    </th>
    0.61
    ए
    0.61
    ك
    0.61
    of
    0.60
    POSITIVE LOGITS
    л
    0.82
     enchant
    0.82
    на
    0.70
     heißt
    0.69
    त
    0.68
     enchanted
    0.68
     healer
    0.68
    ர
    0.68
    ל
    0.66
    ן
    0.66
    Activations Density 0.002%

    No Known Activations