© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 213612
    Prev
    Next
    INDEX
    Explanations

    serve

    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_47_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
     Hua
    0.45
     Fah
    0.42
     faj
    0.41
     Enrico
    0.40
    以下の
    0.40
    fah
    0.39
    ]/*
    0.39
     Allan
    0.39
    اك
    0.39
     नाइट
    0.39
    POSITIVE LOGITS
    ice
    0.89
    Ice
    0.83
     ice
    0.78
    ices
    0.77
    ICE
    0.76
    icing
    0.71
     ICE
    0.71
    iced
    0.71
     Ice
    0.68
    冰
    0.66
    Activations Density 0.001%

    No Known Activations