© 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. 151983
    Prev
    Next
    INDEX
    Explanations

    say "-osion" or "-ension"

    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
     Jorge
    0.43
    "),],
    0.43
     ADA
    0.42
     protruding
    0.42
     ASA
    0.41
    Jorge
    0.40
     Rembrandt
    0.40
    枯
    0.40
    }}_{\
    0.40
     MAPE
    0.39
    POSITIVE LOGITS
    нение
    0.59
    hesion
    0.58
    ension
    0.57
    cision
    0.57
    ision
    0.56
    ersion
    0.55
    exion
    0.55
    ensión
    0.54
    ktion
    0.54
    ression
    0.53
    Activations Density 0.003%

    No Known Activations