© 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. 36942
    Prev
    Next
    INDEX
    Explanations

    crime and fraud

    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
     самое
    0.36
     jump
    0.35
     costruire
    0.34
     pobres
    0.34
     matr
    0.34
     pancake
    0.33
    溏
    0.33
    ён
    0.33
     NAME
    0.32
     komplett
    0.32
    POSITIVE LOGITS
     ಪ್ರಕರಣ
    0.39
    adeon
    0.38
    aced
    0.37
     businesses
    0.36
    ấn
    0.35
     निदेशालय
    0.35
    ዴ
    0.35
    Ẓ
    0.35
    ื่น
    0.35
     extortion
    0.35
    Activations Density 0.005%

    No Known Activations