© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215057
    Prev
    Next
    INDEX
    Explanations

    Terms of Service and policies

    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_31_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
     observable
    0.36
     Verse
    0.36
    ucos
    0.36
     verse
    0.35
     मिळते
    0.35
     Cosa
    0.35
    潺
    0.35
    observable
    0.35
    ানুভূতি
    0.34
    ྡ
    0.34
    POSITIVE LOGITS
     trước
    0.40
     кілько
    0.40
    AppDesigner
    0.40
     Karina
    0.38
    מיד
    0.38
     قبل
    0.38
    ก่อน
    0.38
    ច្រើន
    0.38
    貴重
    0.36
    鴳
    0.36
    Activations Density 0.001%

    No Known Activations