© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129374
    Prev
    Next
    INDEX
    Explanations

    on your plate or in your hands

    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_6_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
    /
    1.15
    ?
    1.12
    ight
    1.02
    ow
    1.01
    ie
    1.00
    ies
    0.97
    ize
    0.95
    it
    0.93
    +
    0.93
    ives
    0.92
    POSITIVE LOGITS
     for
    0.96
    ්ර
    0.87
     источ
    0.80
    са
    0.79
    ни
    0.79
     chrét
    0.78
    деся
    0.78
    которые
    0.77
     ahuv
    0.77
    ారు
    0.77
    Activations Density 0.001%

    No Known Activations