© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 242131
    Prev
    Next
    INDEX
    Explanations

    donate and be a part of

    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_25_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
     amounts
    0.21
     maître
    0.21
     makhluk
    0.20
    ောင့်
    0.20
    的情
    0.20
    {\|
    0.20
    ான்
    0.20
    (__
    0.19
     Roux
    0.19
    ̙
    0.19
    POSITIVE LOGITS
    Big
    0.21
    创新
    0.20
    icill
    0.20
    篇文章
    0.19
     appare
    0.19
    而在
    0.19
    Biggest
    0.19
     उंच
    0.19
    停车场
    0.19
    aspir
    0.19
    Activations Density 0.001%

    No Known Activations