© 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. 65142
    Prev
    Next
    INDEX
    Explanations

    winter

    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
    ֽ
    0.37
     регистрации
    0.36
     owning
    0.36
     ಹೊಂದ
    0.35
    owned
    0.35
     একটা
    0.35
    Ethyl
    0.35
     للا
    0.35
     letech
    0.35
     Bad
    0.35
    POSITIVE LOGITS
     analog
    0.39
    雪
    0.38
    liku
    0.38
     frank
    0.37
    ouna
    0.37
     menyenangkan
    0.37
     stormy
    0.37
    lich
    0.36
    ಾಗಿ
    0.36
     Finder
    0.36
    Activations Density 0.001%

    No Known Activations