© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87086
    Prev
    Next
    INDEX
    Explanations

    specific certain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    ַ
    0.69
    ﻤ
    0.68
    になった
    0.66
    Kana
    0.66
    )$-
    0.64
     نمی‌
    0.63
    となった
    0.62
    Ş
    0.62
    M
    0.61
    М
    0.61
    POSITIVE LOGITS
    ل
    1.32
    л
    0.98
    ن
    0.93
    и
    0.91
    ع
    0.88
    н
    0.88
     is
    0.87
    ца
    0.86
    г
    0.86
    у
    0.84
    Activations Density 0.000%

    No Known Activations