© 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. 14659
    Prev
    Next
    INDEX
    Explanations

    range from 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_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
    ?");
    0.33
     രണ്ട്
    0.31
     duas
    0.30
     щоб
    0.30
     дві
    0.30
    </h6>
    0.30
     పాటు
    0.29
     фотографи
    0.29
     `-
    0.29
     不是
    0.29
    POSITIVE LOGITS
    K
    0.38
    5
    0.36
    6
    0.34
    9
    0.33
    8
    0.32
    bs
    0.31
    he
    0.30
    am
    0.30
    co
    0.30
    My
    0.30
    Activations Density 0.006%

    No Known Activations