© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5026
    Prev
    Next
    INDEX
    Explanations

    theoretical physics and mathematical sciences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_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
     align
    0.37
     ops
    0.34
    thapi
    0.34
     Yukon
    0.33
     dissociated
    0.33
    లా
    0.33
     alignment
    0.32
    鴉
    0.32
     Alignment
    0.31
     Trident
    0.31
    POSITIVE LOGITS
     Theoretical
    0.55
    Theoretical
    0.52
    Cambridge
    0.46
     theoretical
    0.46
     Theoret
    0.46
    Institute
    0.46
     theorists
    0.45
     fizik
    0.45
     Perimeter
    0.44
    Physics
    0.44
    Activations Density 0.015%

    No Known Activations