© 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. 138682
    Prev
    Next
    INDEX
    Explanations

    center

    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
     waxed
    0.40
     sport
    0.39
    갑
    0.38
    Wax
    0.38
     wax
    0.38
    sport
    0.37
     спорт
    0.36
    isecond
    0.35
     flamb
    0.35
    '=
    0.35
    POSITIVE LOGITS
     center
    2.14
     centre
    1.99
    center
    1.89
    センター
    1.86
     Center
    1.84
     CENTER
    1.83
    中心
    1.82
    Center
    1.80
    centre
    1.79
     centro
    1.75
    Activations Density 0.027%

    No Known Activations