© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48158
    Prev
    Next
    INDEX
    Explanations

    partitioning

    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_10_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
    t
    1.24
    y
    0.83
     punkt
    0.74
     demonstrable
    0.70
    na
    0.70
    ਰ
    0.69
    tive
    0.67
     demonstr
    0.67
     модуля
    0.66
    nt
    0.64
    POSITIVE LOGITS
    л
    0.96
     Partition
    0.88
    分区
    0.85
    ти
    0.84
    ну
    0.84
    ล
    0.83
    لوب
    0.82
    лм
    0.82
    partition
    0.80
    اته
    0.80
    Activations Density 0.018%

    No Known Activations