© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 6718
    Prev
    Next
    INDEX
    Explanations

    PowerShell cmdlets and parameters

    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
    চাল
    0.38
     interpretar
    0.38
    চালক
    0.36
    屐
    0.36
     warna
    0.36
     Warna
    0.35
    はい
    0.35
     perencanaan
    0.35
    uanya
    0.35
     информация
    0.35
    POSITIVE LOGITS
     Solutions
    0.40
    olutions
    0.39
    [-
    0.38
    নু
    0.37
    ⃛
    0.36
     solutions
    0.35
    ressa
    0.35
    Solutions
    0.35
     softer
    0.34
     Systeme
    0.34
    Activations Density 0.002%

    No Known Activations