© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36702
    Prev
    Next
    INDEX
    Explanations

    smart contracts

    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_3_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
    то
    1.14
    ة
    1.09
    ق
    1.02
    to
    0.98
    ية
    0.95
    การ
    0.95
    <0x80>
    0.94
    م
    0.91
    не
    0.90
    স
    0.89
    POSITIVE LOGITS
     Kval
    0.63
    ertal
    0.63
     bons
    0.62
    agem
    0.61
    itaj
    0.61
    icato
    0.61
    kode
    0.60
    gewicht
    0.60
    ITÉ
    0.60
     आँख
    0.60
    Activations Density 0.004%

    No Known Activations