© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 88882
    Prev
    Next
    INDEX
    Explanations

    isolate environments

    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_11_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
    ların
    0.67
     ardından
    0.60
     बिक्री
    0.59
    ﻋ
    0.59
     pada
    0.58
     anos
    0.56
     layanan
    0.56
    ayv
    0.56
    EN
    0.56
    ️⃣
    0.55
    POSITIVE LOGITS
    不
    0.59
    Dv
    0.59
     Triton
    0.59
    可以
    0.57
    вам
    0.57
     Dv
    0.56
    Dn
    0.55
    тері
    0.55
     discharges
    0.55
     XXII
    0.55
    Activations Density 0.003%

    No Known Activations