© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 254078
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    Picker
    0.39
    반
    0.35
    梱
    0.35
    zus
    0.35
     ź
    0.35
    建
    0.35
    चाल
    0.34
    商品は
    0.33
    sendKeys
    0.33
    isson
    0.33
    POSITIVE LOGITS
     sw
    0.65
     SW
    0.60
    瑞
    0.55
     свер
    0.54
     SWT
    0.53
     स्वि
    0.52
    SW
    0.52
     Swann
    0.50
     swap
    0.49
    swan
    0.49
    Activations Density 0.000%

    No Known Activations