© 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. 197204
    Prev
    Next
    INDEX
    Explanations

    uppercase U

    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
     hikes
    0.42
     drinks
    0.40
     introductions
    0.40
    荿
    0.39
    סים
    0.38
     rises
    0.37
     nerfs
    0.37
    贬
    0.36
     নীচে
    0.36
     storms
    0.36
    POSITIVE LOGITS
    𝗨
    0.62
    Upp
    0.57
    𝑈
    0.57
    𝐔
    0.57
    Ｕ
    0.57
     Upan
    0.53
    𝕌
    0.51
     Upp
    0.50
    ᵁ
    0.49
    𝓾
    0.49
    Activations Density 0.005%

    No Known Activations