© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242166
    Prev
    Next
    INDEX
    Explanations

    type definition

    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_40_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
    茶叶
    0.42
     материалов
    0.41
     spoiled
    0.40
    Landscape
    0.39
    等於
    0.37
    咖啡
    0.37
     spoilt
    0.37
    ₁+
    0.36
    Tea
    0.36
     Kroger
    0.36
    POSITIVE LOGITS
     klasik
    0.41
     type
    0.41
     urges
    0.40
     urge
    0.40
    जि
    0.37
     Hic
    0.37
     ideal
    0.36
     tipe
    0.36
    ideo
    0.35
    理想
    0.35
    Activations Density 0.000%

    No Known Activations