© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199049
    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_27_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sported
    0.36
     சித்த
    0.35
    unie
    0.35
     wh
    0.34
     Barton
    0.34
    __);
    0.33
    igment
    0.33
     Sediment
    0.33
    Ed
    0.32
     gh
    0.32
    POSITIVE LOGITS
    資料
    0.41
    떳
    0.40
     unicode
    0.39
    values
    0.39
    毘
    0.38
    有好
    0.38
    ляє
    0.37
    なる
    0.37
    اہر
    0.37
    鋯
    0.37
    Activations Density 0.000%

    No Known Activations