© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 247572
    Prev
    Next
    INDEX
    Explanations

    numbers in file names or ids

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
    ymas
    0.40
    eres
    0.39
    coming
    0.39
    ieres
    0.39
    IZE
    0.38
     receptive
    0.38
    ierto
    0.38
    __(/*!
    0.37
    ize
    0.37
     coming
    0.37
    POSITIVE LOGITS
     맨
    0.37
    予告
    0.35
     폴
    0.35
    اش
    0.35
    맨
    0.34
    Ὁ
    0.34
     Ло
    0.34
     बै
    0.34
     મહિ
    0.33
    폴
    0.33
    Activations Density 0.002%

    No Known Activations