© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 150072
    Prev
    Next
    INDEX
    Explanations

    estate

    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_59_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
    ặn
    0.41
    SCUS
    0.37
    پیگنڈ
    0.36
    ﺃ
    0.35
     زید
    0.35
     tran
    0.34
     tumbling
    0.34
    뀝
    0.34
     मंत्रिमंडल
    0.33
    äder
    0.33
    POSITIVE LOGITS
     estates
    0.54
     Estates
    0.50
     estate
    0.45
     Estate
    0.39
    ̰
    0.38
    estate
    0.37
    荅
    0.37
    蓽
    0.37
    ̕
    0.36
     ESTATE
    0.36
    Activations Density 0.046%

    No Known Activations