© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 858
    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_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
     Cau
    0.38
    Cau
    0.37
     scraper
    0.34
     몸
    0.34
    สึก
    0.33
    越し
    0.33
    JobID
    0.33
     Passed
    0.33
    줄
    0.32
     tail
    0.32
    POSITIVE LOGITS
     unit
    2.36
    Unit
    2.17
    unit
    2.16
     Unit
    2.16
     UNIT
    1.87
    UNIT
    1.84
    单位
    1.84
     यूनिट
    1.73
    ユニット
    1.66
     unidad
    1.65
    Activations Density 0.026%

    No Known Activations