© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 63579
    Prev
    Next
    INDEX
    Explanations

    say "upgrade"

    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_59_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
     Up
    2.75
    Up
    2.67
    up
    2.42
     up
    2.33
    アップ
    2.20
     업
    2.17
     upgrade
    2.11
     upgrad
    2.08
    Upgrade
    2.03
    upgrade
    1.98
    POSITIVE LOGITS
    oddsidemargin
    0.36
    骜
    0.36
     Memoirs
    0.35
    兕
    0.35
     باندې
    0.34
     Pickle
    0.33
     appré
    0.33
     Intent
    0.33
     Characters
    0.32
     saffron
    0.32
    Activations Density 0.006%

    No Known Activations