© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 57560
    Prev
    Next
    INDEX
    Explanations

    all / every

    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_59_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
     EVER
    0.44
    Ever
    0.43
    EVER
    0.42
     Ever
    0.40
    詿
    0.39
     ever
    0.39
    ढ़े
    0.36
     đâu
    0.36
    ≜
    0.36
    មួយ
    0.35
    POSITIVE LOGITS
    いた
    2.05
    致
    1.27
     all
    1.27
     いた
    1.24
    至
    1.06
     tất
    1.00
     все
    0.96
     جميع
    0.89
    所有
    0.88
    all
    0.88
    Activations Density 0.012%

    No Known Activations