© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 69507
    Prev
    Next
    INDEX
    Explanations

    relating to order

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    严重的
    0.37
    obar
    0.37
    说什么
    0.37
    בים
    0.36
    effectively
    0.36
    طق
    0.35
    裸
    0.35
     intensified
    0.35
     کف
    0.34
    屒
    0.34
    POSITIVE LOGITS
     चौहान
    0.41
     Ortega
    0.40
     Ми
    0.40
     Order
    0.39
    ús
    0.39
     ORDER
    0.39
     ordem
    0.39
    OrderItem
    0.39
    Hashing
    0.38
    Order
    0.38
    Activations Density 0.000%

    No Known Activations