© 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. 205688
    Prev
    Next
    INDEX
    Explanations

    cherry

    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
    энне
    0.39
    쩡
    0.37
    inet
    0.37
    嗶
    0.37
    Heart
    0.37
     abertura
    0.36
    enteri
    0.36
    开拓
    0.35
    APE
    0.34
    ness
    0.33
    POSITIVE LOGITS
     Cherry
    0.75
     cherries
    0.69
     cherry
    0.68
    Cherry
    0.68
     Cher
    0.63
    cherry
    0.62
    樱
    0.61
    Cher
    0.57
    櫻
    0.54
    Чер
    0.50
    Activations Density 0.001%

    No Known Activations