© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6094
    Prev
    Next
    INDEX
    Explanations

    Twitter threads

    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_40_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
     ਮੰ
    0.38
     papi
    0.37
    edel
    0.35
     mobility
    0.35
    ตี
    0.35
    সাহিত
    0.35
     Stef
    0.34
     पीडीएफ
    0.34
    囲
    0.34
     podr
    0.34
    POSITIVE LOGITS
     thread
    2.22
     Thread
    2.03
    thread
    1.97
     threads
    1.95
    Thread
    1.94
    线程
    1.79
    THREAD
    1.78
     threading
    1.74
     Threads
    1.72
    Threads
    1.59
    Activations Density 0.176%

    No Known Activations