© 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. 30855
    Prev
    Next
    INDEX
    Explanations

    sales volume

    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
     এর
    0.41
     Astor
    0.37
    ಯೇ
    0.37
     ​​
    0.36
    FRED
    0.35
     TOP
    0.35
     scathing
    0.34
    TOP
    0.34
     FRED
    0.34
    龙头
    0.34
    POSITIVE LOGITS
    ಿತಿ
    0.43
    UnityEngine
    0.41
    िलों
    0.40
    lbrack
    0.38
    piro
    0.36
    ূপে
    0.36
    펑
    0.35
    unj
    0.35
    readline
    0.35
     точке
    0.35
    Activations Density 0.001%

    No Known Activations