© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86229
    Prev
    Next
    INDEX
    Explanations

    cheese, Technologies, Rate, Charm, Hait

    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
    لي
    0.95
     создание
    0.73
    鸪
    0.73
     économiques
    0.70
    多い
    0.64
    ாலத்தில்
    0.64
    یم
    0.63
     commandes
    0.63
     executar
    0.63
     عمليات
    0.63
    POSITIVE LOGITS
    s
    0.93
    ม
    0.71
    te
    0.68
    S
    0.62
    ים
    0.61
    assess
    0.61
    Assess
    0.60
    м
    0.58
    ს
    0.58
    SAT
    0.57
    Activations Density 0.013%

    No Known Activations