© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35679
    Prev
    Next
    INDEX
    Explanations

    spray bottle", "paint can"

    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
    ।
    0.93
    س
    0.87
    ،
    0.78
    ي
    0.75
    л
    0.75
    Го
    0.71
    ၎င်း
    0.71
    ಯ
    0.70
    न
    0.70
    determine
    0.66
    POSITIVE LOGITS
    ator
    0.78
    ats
    0.78
    ates
    0.70
    ’
    0.68
     purview
    0.67
    ur
    0.66
     by
    0.66
     of
    0.65
     from
    0.64
    urian
    0.64
    Activations Density 0.001%

    No Known Activations