© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86755
    Prev
    Next
    INDEX
    Explanations

    A sense that

    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_3_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
    á
    0.87
    í
    0.86
    ing
    0.78
    in
    0.75
    ۔
    0.73
    ли
    0.72
    िंग
    0.63
    inine
    0.63
    ê
    0.63
    ру
    0.62
    POSITIVE LOGITS
    ت
    0.81
    ካከል
    0.72
    на
    0.71
     automatis
    0.68
     саме
    0.68
    ع
    0.68
    了很多
    0.66
     ډول
    0.66
     OS
    0.64
    س
    0.64
    Activations Density 0.000%

    No Known Activations