© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 181384
    Prev
    Next
    INDEX
    Explanations

    transitivity (A > B and B > C)

    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_24_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
    ⬥
    0.40
    ază
    0.40
     Remarkably
    0.40
    untas
    0.38
    ządz
    0.38
    imori
    0.38
    द्योगिक
    0.37
    <0x98>
    0.37
    üllen
    0.37
     sincerity
    0.37
    POSITIVE LOGITS
    FUTURE
    0.38
     ಎಂಬುದ
    0.38
    وض
    0.37
     Idani
    0.37
     nek
    0.37
     حاصل
    0.36
     pán
    0.35
    Future
    0.34
    밥
    0.34
     باب
    0.34
    Activations Density 0.002%

    No Known Activations