© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166857
    Prev
    Next
    INDEX
    Explanations

    .

    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_31_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
     griseo
    0.11
    穎
    0.10
     commandBuffer
    0.10
    墉
    0.10
     drawRight
    0.10
    InBuffer
    0.10
     ornamentation
    0.10
     принимать
    0.09
    ╅
    0.09
     कक्कड़
    0.09
    POSITIVE LOGITS
     B
    0.11
     $
    0.10
    0.10
     L
    0.09
    rou
    0.09
     Ba
    0.09
     U
    0.09
     J
    0.09
     Research
    0.09
     &
    0.09
    Activations Density 0.002%

    No Known Activations