© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 175357
    Prev
    Next
    INDEX
    Explanations

    comprehensive answers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    卡
    0.43
     karty
    0.41
    旿
    0.40
     Cards
    0.40
     সম্ম
    0.39
     Court
    0.38
     CART
    0.38
     sorting
    0.38
     Immunology
    0.37
     proyect
    0.37
    POSITIVE LOGITS
     Paso
    0.49
     McLaren
    0.47
     paso
    0.41
    彭
    0.40
     pas
    0.40
     McL
    0.39
     McCl
    0.39
    pas
    0.38
    bare
    0.38
     swollen
    0.38
    Activations Density 0.009%

    No Known Activations