© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7666
    Prev
    Next
    INDEX
    Explanations

    technical domains and syntax

    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_39_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
    懷
    0.42
     कड़ी
    0.39
     junt
    0.38
     beauties
    0.37
     учреждений
    0.37
     বাঁ
    0.36
     उमेद
    0.36
    怀
    0.36
     Lucy
    0.36
     Clamp
    0.35
    POSITIVE LOGITS
     engine
    0.66
    engine
    0.64
     Engine
    0.63
    Engine
    0.61
    processor
    0.61
     processor
    0.60
    引擎
    0.57
     엔진
    0.57
    Processor
    0.54
    エンジン
    0.54
    Activations Density 0.136%

    No Known Activations