© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11212
    Prev
    Next
    INDEX
    Explanations

    as inputs to

    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
    দ্‌
    0.28
    ूद
    0.27
     चरम
    0.27
    )/
    0.25
    份
    0.25
    一份
    0.25
    ㄛ
    0.25
    ;"
    0.25
    resolution
    0.25
     상당
    0.24
    POSITIVE LOGITS
     berl
    0.29
     Bernd
    0.27
    baz
    0.25
    যোগী
    0.24
    ਲਾ
    0.24
    igera
    0.24
    ත්තේ
    0.24
     pedestrians
    0.23
    朗
    0.23
     sejam
    0.23
    Activations Density 0.126%

    No Known Activations