© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43859
    Prev
    Next
    INDEX
    Explanations

    instance capacity and types

    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
    も
    1.11
    在
    1.09
    ના
    1.08
    도
    1.02
    もら
    0.99
    ін
    0.96
    ан
    0.95
    る
    0.94
    с
    0.92
    ين
    0.91
    POSITIVE LOGITS
    0
    1.29
    9
    1.08
    8
    0.88
    ۰
    0.79
     ০৯
    0.77
    7
    0.77
    ן
    0.77
     by
    0.75
     for
    0.74
     sahib
    0.71
    Activations Density 0.000%

    No Known Activations