© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 65861
    Prev
    Next
    INDEX
    Explanations

    islands

    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
     指輪
    0.42
     solle
    0.41
     Mongolian
    0.39
     Mongol
    0.38
    貉
    0.38
    ＮＡ
    0.37
     trivially
    0.37
     ন্যাশনাল
    0.37
     styl
    0.37
     Mandal
    0.37
    POSITIVE LOGITS
    island
    0.60
     island
    0.59
    岛
    0.57
    Island
    0.54
    Tum
    0.52
    tum
    0.48
    섬
    0.48
    島
    0.46
     섬
    0.45
     islas
    0.44
    Activations Density 0.001%

    No Known Activations