© 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. 30708
    Prev
    Next
    INDEX
    Explanations

    say "t" words

    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
    ించడానికి
    0.39
     Gorman
    0.36
     ኤ
    0.35
    marshalN
    0.33
    elementProp
    0.33
    pmatrix
    0.32
    箖
    0.32
     EVP
    0.32
    ුණු
    0.32
    ᱮ
    0.31
    POSITIVE LOGITS
     То
    2.45
     토
    2.42
     TO
    2.39
     Tok
    2.36
    TO
    2.30
     Tos
    2.28
     تو
    2.25
    Tos
    2.23
    토
    2.23
    Tok
    2.22
    Activations Density 0.331%

    No Known Activations