© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45585
    Prev
    Next
    INDEX
    Explanations

    anthrax, anthropic

    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_3_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
    it
    0.94
    pe
    0.72
    פ
    0.72
    是
    0.68
     könne
    0.68
    é
    0.68
    itih
    0.67
    ش
    0.67
    ut
    0.66
    里的
    0.66
    POSITIVE LOGITS
    ας
    0.66
     months
    0.58
     or
    0.57
     target
    0.57
    ेष
    0.56
     December
    0.55
     parochial
    0.55
    ות
    0.55
     architectural
    0.55
     January
    0.54
    Activations Density 0.001%

    No Known Activations