© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 87488
    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_23_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
     चार
    0.45
     प्रिंस
    0.44
    ेंज
    0.44
    지
    0.43
     두
    0.43
     నాలుగు
    0.42
     ۴
    0.42
     대
    0.41
    两个
    0.41
     व
    0.41
    POSITIVE LOGITS
     exercer
    0.57
    رير
    0.57
    ocally
    0.49
     ছুঁ
    0.49
    Questo
    0.48
    .[
    0.48
    বাজার
    0.48
     optar
    0.48
     eigener
    0.46
    \"
    0.46
    Activations Density 0.000%

    No Known Activations