© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54695
    Prev
    Next
    INDEX
    Explanations

    open, very, long, huge

    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_30_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
     nomen
    0.37
    ไม่ได้
    0.37
    并不
    0.37
     nisam
    0.37
    私も
    0.36
     نہیں
    0.35
    決して
    0.35
     echte
    0.35
    },-\
    0.34
    rparam
    0.34
    POSITIVE LOGITS
    killer
    0.39
     forêt
    0.38
    KAR
    0.38
    Killer
    0.36
     kär
    0.36
     Killer
    0.35
     PAGES
    0.35
     FOREST
    0.35
     detd
    0.35
     SPIR
    0.35
    Activations Density 0.043%

    No Known Activations