© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27369
    Prev
    Next
    INDEX
    Explanations

    for

    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_40_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
    ገር
    0.43
     bijoux
    0.37
     이거
    0.33
    iroz
    0.33
    (/*
    0.32
    ய்ட
    0.32
    সজ্জিত
    0.32
    陀
    0.32
    ervi
    0.31
    騰
    0.31
    POSITIVE LOGITS
     which
    1.92
    which
    1.80
     которых
    1.71
     которой
    1.62
     которого
    1.58
     котором
    1.58
     WHICH
    1.55
     Which
    1.55
    Which
    1.51
     których
    1.50
    Activations Density 0.096%

    No Known Activations