© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 244554
    Prev
    Next
    INDEX
    Explanations

    complete

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Rae
    0.41
    নাত
    0.40
    ణులు
    0.38
     ഓരോ
    0.37
     लिमिट
    0.36
    ρες
    0.35
    ཆ
    0.35
    teles
    0.34
    䢔
    0.34
     ())
    0.34
    POSITIVE LOGITS
     completely
    1.95
    完全
    1.80
     Completely
    1.75
     completamente
    1.66
    completely
    1.63
     totally
    1.54
     úpl
    1.52
     complètement
    1.50
     完全
    1.49
     완전히
    1.43
    Activations Density 0.171%

    No Known Activations