© 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-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 2939
    Prev
    Next
    INDEX
    Explanations

    app.use(

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
    лно
    1.40
    о
    1.38
    
    1.22
    ঁজ
    1.20
    рованный
    1.19
    ‌ന
    1.17
    Lifecycle
    1.15
    
    1.15
    ‌های
    1.13
    ▫
    1.12
    POSITIVE LOGITS
    jangan
    1.41
     trifft
    1.38
    robes
    1.34
     toucher
    1.32
     organise
    1.31
     diethyl
    1.30
    adies
    1.30
    izzati
    1.30
     petits
    1.30
     filets
    1.29
    Activations Density 0.001%

    No Known Activations