© 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. 2585
    Prev
    Next
    INDEX
    Explanations

    address components

    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
    emans
    0.45
     Boulevard
    0.39
    imper
    0.38
     tarses
    0.37
    iland
    0.37
    쿄
    0.37
     Cedex
    0.36
    ...";
    0.36
     twenty
    0.35
     Failing
    0.35
    POSITIVE LOGITS
     ১৩২১
    0.43
    XXXX
    0.40
    १८४
    0.39
     הז
    0.38
    xxxx
    0.38
     ہزار
    0.35
    স্তর
    0.35
    xffff
    0.34
    Ox
    0.33
     Thousands
    0.33
    Activations Density 0.025%

    No Known Activations