© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54712
    Prev
    Next
    INDEX
    Explanations

    Moringa, Lions Mane, Maca, Spirulina

    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_31_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
     beat
    0.28
     Beat
    0.26
    beat
    0.26
    Beat
    0.25
     퇴
    0.25
     Deposit
    0.24
     과학
    0.22
     payee
    0.22
     Tender
    0.22
     solicitar
    0.21
    POSITIVE LOGITS
     powders
    0.24
    monary
    0.24
     powder
    0.23
     coatings
    0.23
     रीति
    0.22
    йин
    0.22
    ToShow
    0.21
    谌
    0.21
    рья
    0.21
    gwood
    0.21
    Activations Density 0.008%

    No Known Activations