© 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. 65720
    Prev
    Next
    INDEX
    Explanations

    orange

    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
    误
    0.37
     Tibet
    0.37
    淄
    0.37
     ferment
    0.37
     Jensen
    0.37
     Tia
    0.37
     زا
    0.36
     Yesus
    0.36
    iyon
    0.35
     Wey
    0.35
    POSITIVE LOGITS
     orange
    2.05
     Orange
    1.91
    Orange
    1.89
    orange
    1.88
    オレンジ
    1.69
     oranges
    1.66
     naranja
    1.66
    橙
    1.59
     laranja
    1.51
     orang
    1.45
    Activations Density 0.014%

    No Known Activations