© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79182
    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
    דר
    0.39
     networks
    0.38
     тип
    0.38
    षे
    0.38
     broadcast
    0.37
    NED
    0.36
    "]));
    0.36
     Μ
    0.36
     buildTypes
    0.36
    Μ
    0.36
    POSITIVE LOGITS
    Notebook
    0.42
    するための
    0.38
    ivably
    0.38
    Plaintiff
    0.37
    oseconds
    0.36
    贯彻
    0.35
     উচ্চ
    0.34
     शॉर्ट
    0.34
    当中
    0.34
    nań
    0.34
    Activations Density 0.000%

    No Known Activations