© 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. 24901
    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
     water
    0.58
    水
    0.55
     वॉटर
    0.49
     WATER
    0.48
    WATER
    0.48
     Water
    0.48
    water
    0.46
     वाटर
    0.46
    Water
    0.45
     nước
    0.43
    POSITIVE LOGITS
     c
    0.49
    rrbracket
    0.42
     EPS
    0.40
    EPS
    0.39
     Park
    0.38
    jv
    0.37
    pts
    0.36
    মধ
    0.36
     Ever
    0.36
     Ivory
    0.36
    Activations Density 0.000%

    No Known Activations