© 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. 115400
    Prev
    Next
    INDEX
    Explanations

    "so" introducing questions or elaborations

    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
    Not in Any Lists

    No Comments

    Negative Logits
    টী
    0.32
     Итак
    0.30
    тного
    0.29
    emonic
    0.29
     şeyi
    0.29
    瘴
    0.29
    🖼
    0.28
    metaTag
    0.28
     महीना
    0.28
     напол
    0.27
    POSITIVE LOGITS
     only
    0.31
     minimally
    0.31
    籲
    0.29
     therapeut
    0.29
     both
    0.28
     clinically
    0.28
    仅
    0.28
     ali
    0.28
     axial
    0.28
     foi
    0.28
    Activations Density 0.001%

    No Known Activations