© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 143777
    Prev
    Next
    INDEX
    Explanations

    <

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    uarine
    0.38
     heures
    0.38
    黒
    0.38
    Retrie
    0.37
    viruses
    0.37
    helicopter
    0.37
    Harvest
    0.37
    Inspection
    0.36
    Trajectories
    0.36
    ithmet
    0.36
    POSITIVE LOGITS
     revol
    0.43
     cools
    0.43
     sulf
    0.39
     gabb
    0.37
    aches
    0.37
    頬
    0.37
    oclip
    0.36
    igh
    0.36
    usch
    0.36
    igl
    0.36
    Activations Density 0.000%

    No Known Activations