© 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. 141113
    Prev
    Next
    INDEX
    Explanations

    epithelial endothelial cells

    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
     مو
    0.40
    ٹس
    0.39
     ނ
    0.38
     Verenig
    0.38
    COUVER
    0.38
    vais
    0.37
    डिशा
    0.37
     pivoted
    0.36
    雨
    0.36
    athu
    0.36
    POSITIVE LOGITS
     डीआर
    0.40
     cites
    0.37
     Yankee
    0.36
    layer
    0.36
     Mankind
    0.35
     zio
    0.35
    Layer
    0.35
    站点
    0.35
    chanical
    0.34
    싼
    0.34
    Activations Density 0.001%

    No Known Activations