© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 155489
    Prev
    Next
    INDEX
    Explanations

    /

    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
     Pleasure
    0.46
     Platte
    0.42
    bride
    0.38
    cor
    0.38
     pleasure
    0.37
    赏
    0.37
    ادری
    0.36
     equil
    0.36
     作り
    0.36
    쁠
    0.35
    POSITIVE LOGITS
    Tinh
    0.43
     ре
    0.41
     Ring
    0.38
    戝
    0.38
    Ring
    0.38
    ার্টমেন্ট
    0.38
    fifths
    0.38
     Тере
    0.38
    Kai
    0.38
     TEC
    0.37
    Activations Density 0.000%

    No Known Activations