© 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. 48001
    Prev
    Next
    INDEX
    Explanations

    text and images

    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
     Ensuring
    0.38
     ξεκ
    0.38
     addBook
    0.37
     источ
    0.36
     জন্ত
    0.35
    γρά
    0.35
     DW
    0.34
     esfuerzos
    0.34
    蜿
    0.34
     Finding
    0.33
    POSITIVE LOGITS
     Aegean
    0.40
     Bedien
    0.39
     volcano
    0.37
     tingling
    0.37
     perceives
    0.37
    ssdk
    0.35
    mess
    0.35
     Rimini
    0.35
    Careers
    0.35
    ('/').
    0.35
    Activations Density 0.009%

    No Known Activations