© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193222
    Prev
    Next
    INDEX
    Explanations

    GM suppliers

    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_27_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
     encontrada
    0.38
     एनर्जी
    0.37
    Found
    0.36
    䏍
    0.36
    ड्रन
    0.36
     अलै
    0.36
    postion
    0.36
    Qualified
    0.36
    ǹ
    0.35
    ٕ
    0.35
    POSITIVE LOGITS
     독
    0.36
    phal
    0.35
     বঙ্গের
    0.35
     pancakes
    0.35
    स्कृत
    0.34
     Arno
    0.34
     belly
    0.33
     relocated
    0.33
     victim
    0.32
     Armenian
    0.32
    Activations Density 0.002%

    No Known Activations