© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27387
    Prev
    Next
    INDEX
    Explanations

    path components (__dirname, file, dirname)

    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_10_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
    ed
    1.20
     các
    0.88
    es
    0.85
     skóry
    0.84
     formada
    0.80
    şe
    0.79
    \
    0.79
     américaine
    0.79
    u
    0.78
     Họ
    0.78
    POSITIVE LOGITS
    ک
    0.84
    یر
    0.79
    ند
    0.76
    fledged
    0.71
    中で
    0.66
    博物館
    0.66
    تان
    0.66
    ס
    0.65
    نا
    0.64
     revamp
    0.64
    Activations Density 0.003%

    No Known Activations