© 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. 145460
    Prev
    Next
    INDEX
    Explanations

    ped

    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
    Ring
    0.42
    en
    0.41
    漏
    0.41
    ringar
    0.40
    ring
    0.40
    af
    0.40
    Strong
    0.40
    olf
    0.40
    aff
    0.39
    ESA
    0.39
    POSITIVE LOGITS
     rade
    0.45
     BUDGET
    0.41
     ime
    0.39
     rite
    0.39
     DAVIS
    0.38
     ś
    0.38
     stil
    0.38
     goddess
    0.36
     uts
    0.36
     s
    0.36
    Activations Density 0.000%

    No Known Activations