© 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. 4323
    Prev
    Next
    INDEX
    Explanations

    code functions and structures

    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
    DEP
    0.38
    phil
    0.38
    myapplication
    0.38
    随
    0.37
    δει
    0.36
    兌
    0.36
    si
    0.35
    SI
    0.35
    bre
    0.35
    Phil
    0.34
    POSITIVE LOGITS
    asz
    0.43
      
    0.43
     ं
    0.41
    <0x16>
    0.41
    
    0.38
     ۔
    0.37
     расходов
    0.37
     ्
    0.36
     purpos
    0.36
    <0x1D>
    0.36
    Activations Density 0.597%

    No Known Activations