© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 47084
    Prev
    Next
    INDEX
    Explanations

    then, after, next

    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_13_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
     ដើម្បី
    0.55
    ↝
    0.55
    rosa
    0.54
    ♖
    0.54
     nyní
    0.52
    的多
    0.52
    昆
    0.52
    ≐
    0.52
     ১২
    0.51
     قلي
    0.51
    POSITIVE LOGITS
    o
    0.59
     Y
    0.55
    ό
    0.54
     other
    0.53
     employment
    0.53
     unconditional
    0.53
    J
    0.53
     z
    0.52
     chur
    0.52
     Yogyakarta
    0.52
    Activations Density 0.017%

    No Known Activations