© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166732
    Prev
    Next
    INDEX
    Explanations

    two

    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_31_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
     seem
    0.31
     vary
    0.30
     Филип
    0.29
     wurden
    0.28
    ｒ
    0.28
    alted
    0.28
     are
    0.27
     diffe
    0.27
     colegas
    0.27
    ကား
    0.27
    POSITIVE LOGITS
    juje
    0.30
    カジュアル
    0.30
    搶
    0.30
    ዱ
    0.29
     તેની
    0.28
    抢
    0.28
     двох
    0.27
     ਨੂੰ
    0.27
    ড়
    0.26
     interchangeable
    0.26
    Activations Density 0.001%

    No Known Activations