© 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. 145676
    Prev
    Next
    INDEX
    Explanations

    Well

    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
     (
    0.60
     done
    0.46
     written
    0.44
     (\
    0.42
     though
    0.40
     (“
    0.40
    (
    0.40
     (‘
    0.40
     does
    0.39
    oghi
    0.38
    POSITIVE LOGITS
     said
    1.09
    Said
    1.06
    said
    1.00
     Said
    0.95
     گفت
    0.81
    前記
    0.76
     сказал
    0.75
    گفت
    0.74
     dijo
    0.73
     faid
    0.70
    Activations Density 0.001%

    No Known Activations