© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 64074
    Prev
    Next
    INDEX
    Explanations

    say "e" 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_59_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
     э
    0.61
    잤
    0.48
     에
    0.43
     エ
    0.39
     ई
    0.38
    Į
    0.38
    ඔ
    0.38
    আ
    0.37
    plaza
    0.37
    যখন
    0.35
    POSITIVE LOGITS
    ec
    1.59
    ed
    1.58
    e
    1.57
    ep
    1.54
    es
    1.50
    eb
    1.48
    ek
    1.46
    ef
    1.46
    est
    1.45
    е
    1.44
    Activations Density 0.143%

    No Known Activations