© 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. 51294
    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
    தொ
    0.40
    吾
    0.39
     AP
    0.37
     setup
    0.37
     usage
    0.36
    setup
    0.36
     buildup
    0.36
     setups
    0.36
    ăș
    0.36
     usages
    0.35
    POSITIVE LOGITS
    skih
    0.37
    atinib
    0.36
    تقد
    0.35
    gré
    0.34
    დის
    0.34
    陞
    0.34
    র্ক
    0.34
     डिस्कस
    0.34
     ني
    0.34
     regresa
    0.34
    Activations Density 0.000%

    No Known Activations