© 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. 221365
    Prev
    Next
    INDEX
    Explanations

    to explain

    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
     reminded
    0.40
    льность
    0.40
    পরিস
    0.40
     জানিয়ে
    0.39
     আভাস
    0.39
     ግ
    0.38
     entendido
    0.38
    iming
    0.37
     বোঝার
    0.37
    告訴
    0.37
    POSITIVE LOGITS
     musicales
    0.38
    গত
    0.37
    |+
    0.36
    ეტ
    0.35
     musical
    0.35
     architectural
    0.34
     paul
    0.34
    Chois
    0.34
     PAUL
    0.33
    수록
    0.33
    Activations Density 0.001%

    No Known Activations