© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 148911
    Prev
    Next
    INDEX
    Explanations

    0

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    0
    0.74
    3
    0.73
    4
    0.62
    2
    0.57
    5
    0.52
     last
    0.50
    6
    0.46
    last
    0.43
    1
    0.42
    uws
    0.41
    POSITIVE LOGITS
     May
    0.54
     March
    0.49
     __
    0.47
     MARCH
    0.46
     February
    0.45
     "#
    0.44
    May
    0.44
     봄
    0.44
     December
    0.43
     (__
    0.43
    Activations Density 0.002%

    No Known Activations