© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 94141
    Prev
    Next
    INDEX
    Explanations

    task/parameter

    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_60_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
    The
    0.48
    Holds
    0.45
    Royal
    0.42
    <0x0D>
    0.39
    At
    0.39
     orderService
    0.39
    modelVersion
    0.38
    (
    0.38
    Portland
    0.38
     newLine
    0.37
    POSITIVE LOGITS
     Aufgabe
    0.54
    ი
    0.54
     parametrized
    0.54
    پر
    0.53
     figur
    0.52
     task
    0.51
     paramet
    0.51
     parametr
    0.50
    يّ
    0.50
    paramet
    0.49
    Activations Density 0.000%

    No Known Activations