© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51397
    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_31_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
    阶
    0.40
    bilder
    0.39
    新冠
    0.38
    )},
    0.37
     لوگ
    0.36
    图片
    0.36
    წ
    0.36
    階
    0.36
    Pictures
    0.35
     мати
    0.35
    POSITIVE LOGITS
     mú
    0.37
     topping
    0.36
    Une
    0.36
     quantidades
    0.36
     performances
    0.34
     Une
    0.34
     bottom
    0.34
     lop
    0.34
     topper
    0.34
     bits
    0.34
    Activations Density 0.000%

    No Known Activations