© 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. 251693
    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
    본
    0.63
     본
    0.57
    本
    0.51
     bản
    0.46
    本セット
    0.41
    เหน
    0.39
    本项目
    0.38
     本
    0.37
    尕
    0.37
     noticeable
    0.36
    POSITIVE LOGITS
     re
    0.43
     gt
    0.40
    dings
    0.39
     GT
    0.38
    ု
    0.37
    bei
    0.37
    终于
    0.36
     incorpor
    0.36
     லி
    0.36
     लाभकारी
    0.35
    Activations Density 0.000%

    No Known Activations