© 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. 195286
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     sub
    0.40
     folders
    0.39
     Apk
    0.38
    igration
    0.37
     Apps
    0.37
    พอ
    0.36
    andr
    0.36
    wany
    0.35
    요
    0.35
    innerHTML
    0.35
    POSITIVE LOGITS
    Suz
    0.40
     പല
    0.40
    灲
    0.40
     JK
    0.39
    ുകള
    0.38
    Numerous
    0.38
     चौथे
    0.38
     числе
    0.37
     Numerous
    0.36
     तीसरे
    0.35
    Activations Density 0.003%

    No Known Activations