© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 252369
    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_56_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
    Cars
    0.51
    間
    0.50
    间
    0.48
     Automobiles
    0.47
    cars
    0.46
     cars
    0.46
     Cars
    0.46
     automobile
    0.45
    汽车
    0.44
    Veh
    0.44
    POSITIVE LOGITS
    台
    1.45
    臺
    1.18
     台
    1.16
    台上
    1.01
     tai
    0.99
    Tai
    0.97
     Tai
    0.90
    台中
    0.90
    tai
    0.77
     Đài
    0.75
    Activations Density 0.000%

    No Known Activations