© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 215845
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     Brushed
    0.39
    巣
    0.38
    图
    0.38
    😤
    0.38
     Glass
    0.37
     বাসন
    0.37
     accuses
    0.37
     linguaggio
    0.37
    蹰
    0.37
     glass
    0.37
    POSITIVE LOGITS
     Bah
    0.45
    Bart
    0.44
    Mex
    0.44
    tte
    0.44
    ตุ
    0.40
     उत्‍
    0.40
    Water
    0.40
     Franciscan
    0.40
    mex
    0.39
     Tim
    0.38
    Activations Density 0.000%

    No Known Activations