© 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. 45579
    Prev
    Next
    INDEX
    Explanations

    deadpan delivery

    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
    のもの
    0.98
    괵
    0.92
    的价格
    0.82
     généraux
    0.80
     кораб
    0.76
    的变化
    0.75
    ເຄື່ອງ
    0.74
    的操作
    0.72
     flancs
    0.72
     fiabilité
    0.72
    POSITIVE LOGITS
    ح
    1.06
    ↵↵
    1.02
    L
    1.01
    2
    0.89
    ر
    0.82
    ↵
    0.82
    ade
    0.77
    د
    0.77
    ↵↵↵↵
    0.75
    D
    0.75
    Activations Density 0.001%

    No Known Activations