© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 161418
    Prev
    Next
    INDEX
    Explanations

    dictionary where

    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
    Negative Logits
    Terminal
    0.39
    Periph
    0.38
    DUCT
    0.37
    ])/
    0.36
    ![](
    0.35
     peripheral
    0.34
    )]),
    0.34
    ([],
    0.34
    Background
    0.34
    汶
    0.34
    POSITIVE LOGITS
    illustration
    0.41
     Kao
    0.40
     ditu
    0.40
     Juni
    0.40
     Illustrator
    0.40
     kall
    0.39
     Produktions
    0.39
     fry
    0.39
     Tada
    0.38
     illustration
    0.38
    Activations Density 0.005%

    No Known Activations