© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 200518
    Prev
    Next
    INDEX
    Explanations

    abbreviations

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    p
    0.52
    েবে
    0.46
     Ogden
    0.43
    Ps
    0.41
     exon
    0.39
     எட்டு
    0.39
    ps
    0.39
    پی
    0.39
    پ
    0.39
    პ
    0.37
    POSITIVE LOGITS
    NC
    0.61
    nc
    0.55
    NL
    0.50
    apolis
    0.46
    Nc
    0.46
    NY
    0.46
    NCC
    0.46
    НК
    0.45
    NS
    0.45
     NC
    0.45
    Activations Density 0.068%

    No Known Activations