© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6281
    Prev
    Next
    INDEX
    Explanations

    before vs after

    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
    ളി
    0.39
    獃
    0.37
    listdir
    0.35
    ctxt
    0.35
    얼
    0.34
     dnev
    0.32
    //$
    0.32
    鬃
    0.32
    ophor
    0.31
     പ്രേ
    0.31
    POSITIVE LOGITS
     versus
    0.88
    versus
    0.83
     vs
    0.82
     Versus
    0.79
     Vs
    0.75
    vs
    0.74
    Vs
    0.65
     बनाम
    0.59
     VS
    0.54
    VS
    0.54
    Activations Density 0.137%

    No Known Activations