© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13477
    Prev
    Next
    INDEX
    Explanations

    soluble fiber

    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
     kit
    0.28
    ReadFile
    0.25
    套
    0.24
    Electronic
    0.23
    aniu
    0.23
     套
    0.23
    itized
    0.23
     downed
    0.22
     Electronic
    0.22
    മ്ബ
    0.22
    POSITIVE LOGITS
     Henson
    0.24
     Fiber
    0.24
     Vog
    0.23
     peanut
    0.22
    Fiber
    0.22
    麺
    0.22
     Vogt
    0.22
    },{"
    0.21
     fiber
    0.21
     Sarmiento
    0.21
    Activations Density 0.002%

    No Known Activations