© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 30295
    Prev
    Next
    INDEX
    Explanations

    connecting clauses or punctuation

    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_10_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
    4
    0.21
    5
    0.20
     tohoto
    0.20
     questo
    0.19
     jde
    0.19
     certificat
    0.19
     preko
    0.19
    3
    0.18
     reversible
    0.18
     kuri
    0.18
    POSITIVE LOGITS
    지
    0.26
    ków
    0.23
    สังคม
    0.21
    nya
    0.21
    se
    0.21
    ta
    0.20
    kę
    0.20
    inę
    0.20
    in
    0.20
    ształ
    0.19
    Activations Density 0.337%

    No Known Activations