© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 68499
    Prev
    Next
    INDEX
    Explanations

    waxing

    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
    Not in Any Lists

    No Comments

    Negative Logits
    难
    0.40
     přep
    0.38
    transpose
    0.38
     насто
    0.38
    豆腐
    0.37
    เซล
    0.37
    PLEX
    0.36
    ze
    0.35
     Patron
    0.35
     choice
    0.35
    POSITIVE LOGITS
     waxing
    0.42
    ⸨
    0.38
    Ranking
    0.37
    Amazon
    0.36
     cv
    0.36
     waxed
    0.36
    嘴角
    0.36
    ərb
    0.36
     wink
    0.36
    Amanda
    0.35
    Activations Density 0.000%

    No Known Activations