© 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. 11244
    Prev
    Next
    INDEX
    Explanations

    only / do not

    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
    واصل
    0.37
    UNRELATED
    0.37
    \";
    0.36
    ?";
    0.35
     최대한
    0.35
    箬
    0.34
     ছ
    0.34
    клю
    0.34
     continuare
    0.34
    "</
    0.34
    POSITIVE LOGITS
     only
    0.71
    only
    0.65
    只
    0.65
     Only
    0.65
    Only
    0.60
     только
    0.60
     chỉ
    0.57
     只
    0.54
     толькі
    0.51
     wise
    0.51
    Activations Density 0.388%

    No Known Activations