© 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. 129779
    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
    dport
    0.40
     ইসলামাবাদ
    0.40
    넌
    0.39
     fp
    0.38
    kaŭ
    0.37
    里程
    0.37
     جا
    0.37
    ྔ
    0.36
     Beginning
    0.35
     IAC
    0.35
    POSITIVE LOGITS
    etragen
    0.41
    oidal
    0.39
    oids
    0.38
     ус
    0.38
    store
    0.38
    ல்
    0.37
     জনের
    0.37
    ulosic
    0.37
    thi
    0.37
    ül
    0.37
    Activations Density 0.000%

    No Known Activations