© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 37219
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     Cib
    0.47
     Cid
    0.41
     absorb
    0.40
    गम
    0.38
    Ben
    0.38
    积
    0.38
     absorbs
    0.38
     cig
    0.38
     Cig
    0.37
     mab
    0.37
    POSITIVE LOGITS
    Hast
    0.40
    adur
    0.39
     المحاضره
    0.38
    MediaPath
    0.38
    rte
    0.37
    Twenty
    0.37
    🛤
    0.37
    rije
    0.36
    anggung
    0.36
    талия
    0.36
    Activations Density 0.000%

    No Known Activations