© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 8849
    Prev
    Next
    INDEX
    Explanations

    words that contain the letters "az" or "ag" and the letters "di" anywhere in subsequent word

    oai_token-act-pair · gemini-2.0-flash

    Non-english language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     חיצוניים
    -0.65
     الحره
    -0.54
    ini
    -0.50
    fromCharCode
    -0.49
     Polymers
    -0.47
     sessionFactory
    -0.45
     handker
    -0.45
     contextLoads
    -0.44
    in
    -0.43
    liato
    -0.43
    POSITIVE LOGITS
    ıyordu
    1.05
    ılıyor
    1.01
    acağı
    0.96
    ırken
    0.93
    ıyors
    0.91
    ıldığı
    0.90
    ılmıştır
    0.88
    ıyoruz
    0.87
    acaktır
    0.84
    ıştı
    0.84
    Activations Density 2.810%

    No Known Activations