© 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. 195452
    Prev
    Next
    INDEX
    Explanations

    Rufus tool

    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
    Streak
    0.46
    交換
    0.43
    streak
    0.42
    тива
    0.40
    स्वरूप
    0.39
    ]==
    0.38
     constancy
    0.38
    Martin
    0.38
    LEMN
    0.38
     Streak
    0.38
    POSITIVE LOGITS
     exe
    0.41
     Flex
    0.39
     flexion
    0.39
    joner
    0.39
     ಗು
    0.38
    ພ
    0.38
    holt
    0.38
    働
    0.37
    enia
    0.37
    ourism
    0.37
    Activations Density 0.000%

    No Known Activations