© 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. 219
    Prev
    Next
    INDEX
    Explanations

    international number formats

    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
     Bag
    0.41
    പ്പെട്ട
    0.41
    దవ
    0.37
    ్రె
    0.36
     '[
    0.36
    ಮಾಣ
    0.36
    (/(
    0.36
    寔
    0.36
     ['$
    0.36
     Fisherman
    0.36
    POSITIVE LOGITS
    anchi
    0.41
    nega
    0.41
    rous
    0.40
    nous
    0.40
     लीला
    0.38
    neg
    0.38
     dxc
    0.38
    牀
    0.37
    碰
    0.37
    ूं
    0.36
    Activations Density 0.044%

    No Known Activations