© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32667
    Prev
    Next
    INDEX
    Explanations

    documentclass

    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_50_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
    ଂ
    0.39
     timed
    0.37
     久
    0.36
    抿
    0.36
     chal
    0.35
    眄
    0.35
    ind
    0.34
     ఒ
    0.34
     Servlet
    0.34
     analogs
    0.34
    POSITIVE LOGITS
    Ｌ
    0.44
    Ꮮ
    0.40
    アート
    0.40
    **.
    0.40
    venes
    0.39
    Ǧ
    0.38
    Art
    0.37
    ariş
    0.37
     Document
    0.36
    /****
    0.36
    Activations Density 0.000%

    No Known Activations