© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7667
    Prev
    Next
    INDEX
    Explanations

    Options, plans, or categories

    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_39_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
     B
    0.29
     LED
    0.29
    фи
    0.29
     surprising
    0.28
     surprisingly
    0.28
     bern
    0.28
    baru
    0.27
     Ph
    0.27
    dr
    0.27
     transparent
    0.26
    POSITIVE LOGITS
    UCLE
    0.33
    蜮
    0.33
    ত্যা
    0.31
     ecclesiastical
    0.31
    setKeepCallback
    0.31
    雳
    0.31
    ḕ
    0.31
     మాట్లాడు
    0.30
    myItemId
    0.30
     Ease
    0.30
    Activations Density 0.025%

    No Known Activations