© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203794
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_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
    th
    1.07
    це
    0.99
    of
    0.92
    ку
    0.91
     attén
    0.90
    Y
    0.89
    ைட்
    0.88
    ীয়
    0.87
    ຂອງ
    0.87
    pixels
    0.86
    POSITIVE LOGITS
    ot
    1.19
    い
    1.03
    ના
    1.00
    j
    0.98
    et
    0.96
    ‌تر
    0.94
    il
    0.93
    ره
    0.90
    int
    0.88
    ர
    0.87
    Activations Density 0.000%

    No Known Activations