© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 29806
    Prev
    Next
    INDEX
    Explanations

    kick scooters, lean-to, Grow With You, carry-on

    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
    Negative Logits
    Opts
    0.38
    bitflag
    0.37
     Kore
    0.36
     Mugh
    0.35
    िशन
    0.35
     busting
    0.35
     bust
    0.34
    isserie
    0.34
    哭
    0.34
     कौशिक
    0.33
    POSITIVE LOGITS
     Features
    0.37
    ñada
    0.36
     प्रतिनिध
    0.36
     Photon
    0.36
     Feature
    0.36
     Fuel
    0.36
     मंड
    0.36
    نې
    0.36
     いや
    0.35
     Lean
    0.35
    Activations Density 0.019%

    No Known Activations