© 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. 6004
    Prev
    Next
    INDEX
    Explanations

    supreme court cases

    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
     σκ
    0.40
    大学
    0.39
     Cheat
    0.37
    ätzung
    0.36
     dimanche
    0.36
     lied
    0.36
     Dress
    0.35
     것이다
    0.35
    Ꮭ
    0.35
     निघ
    0.35
    POSITIVE LOGITS
    clientHeight
    0.50
    сиз
    0.39
     waivers
    0.38
     فونی
    0.38
     foreclosure
    0.37
     RIM
    0.37
    ichts
    0.37
    hank
    0.37
    colorPrimary
    0.37
    centi
    0.36
    Activations Density 0.016%

    No Known Activations