© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 37197
    Prev
    Next
    INDEX
    Explanations

    quotes

    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_50_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
    Con
    0.43
    ชน
    0.38
    Dent
    0.36
     С
    0.36
     reverses
    0.36
    Gib
    0.36
     gib
    0.35
     osu
    0.35
    簡
    0.35
     Τ
    0.35
    POSITIVE LOGITS
     fudai
    0.41
    olutely
    0.40
    지막
    0.39
    িমূলক
    0.39
    melidir
    0.39
    বরের
    0.39
    drav
    0.38
    䀠
    0.38
    惺
    0.38
    žio
    0.37
    Activations Density 0.008%

    No Known Activations