© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19778
    Prev
    Next
    INDEX
    Explanations

    fraternity and sorority organizations

    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_15_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
     .
    0.49
     Parrish
    0.47
     juggle
    0.46
    गढ़
    0.46
    Ки
    0.45
     foreign
    0.45
     teacher
    0.44
     بھارت
    0.44
     flea
    0.44
    eroy
    0.43
    POSITIVE LOGITS
    istische
    0.48
    衽
    0.46
    ினான்
    0.45
    Isn
    0.44
     lezen
    0.44
    いつ
    0.43
    elijke
    0.42
     scones
    0.42
    াবেন
    0.42
     acht
    0.42
    Activations Density 0.001%

    No Known Activations