© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9872
    Prev
    Next
    INDEX
    Explanations

    ну followed by filler words

    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_13_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
    یه
    0.55
    螟
    0.55
     where
    0.54
    BBC
    0.54
    ю
    0.53
    و
    0.53
     DMEM
    0.52
    ی
    0.51
    ائی
    0.50
    Ahmed
    0.50
    POSITIVE LOGITS
     చేసిన
    0.54
     класс
    0.54
     разговари
    0.53
    das
    0.51
    ratos
    0.51
    ສຸດ
    0.51
     സർ
    0.51
     Laptop
    0.49
     Cosmos
    0.49
     Settlement
    0.48
    Activations Density 0.001%

    No Known Activations