© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 140053
    Prev
    Next
    INDEX
    Explanations

    membrane

    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_46_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
     ^{-
    0.40
    ウンド
    0.39
    计
    0.38
     Creed
    0.37
     quarters
    0.36
     jav
    0.36
    travis
    0.36
    ◸
    0.36
     Cheryl
    0.35
     Milo
    0.35
    POSITIVE LOGITS
     membrane
    0.82
     membranes
    0.71
     Membrane
    0.71
    membrane
    0.68
     мем
    0.66
     membrana
    0.65
     membr
    0.64
     membran
    0.63
     transmembrane
    0.63
    膜
    0.62
    Activations Density 0.001%

    No Known Activations