© 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. 16243
    Prev
    Next
    INDEX
    Explanations

    calling for actions or changes

    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
    练习
    0.40
    Award
    0.40
    ربي
    0.38
     contests
    0.38
     latch
    0.38
     फार
    0.37
    க்கண
    0.37
     award
    0.37
     desafio
    0.37
    형
    0.37
    POSITIVE LOGITS
     appeals
    0.41
     помо
    0.40
     appealed
    0.39
     appeal
    0.38
    ンテ
    0.38
     shrank
    0.37
     Giv
    0.37
     Appeal
    0.37
     Appeals
    0.36
     calling
    0.36
    Activations Density 0.002%

    No Known Activations