© 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. 151984
    Prev
    Next
    INDEX
    Explanations

    communication verbs

    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
     when
    0.55
     quando
    0.54
     WHEN
    0.54
     cuando
    0.54
     Quando
    0.53
     khi
    0.49
     när
    0.48
     wanneer
    0.47
     ketika
    0.46
    儅
    0.46
    POSITIVE LOGITS
    Say
    0.68
    say
    0.55
    And
    0.52
     Say
    0.52
    Flow
    0.48
    Email
    0.47
    Task
    0.46
    For
    0.46
    Remote
    0.46
    Résumé
    0.45
    Activations Density 0.000%

    No Known Activations