© 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. 30431
    Prev
    Next
    INDEX
    Explanations

    even if you don't realize it

    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
     boredom
    0.40
    lazy
    0.39
     mischiev
    0.38
     laziness
    0.38
    শিংটন
    0.37
     пример
    0.36
     monotonous
    0.36
    Scheduler
    0.35
     любое
    0.35
    ㄤ
    0.35
    POSITIVE LOGITS
    名称
    0.37
     اسم
    0.35
    微微
    0.35
     kalah
    0.34
     عنوان
    0.34
     Quant
    0.33
     Instruments
    0.33
    executive
    0.33
    instruments
    0.33
     Ability
    0.33
    Activations Density 0.000%

    No Known Activations