© 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
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 354
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and theorems with associated symbols

    oai_token-act-pair · gemini-2.0-flash

    assume

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     ویکی‌پدی
    -0.82
    DeleteBehavior
    -0.77
    RegistryLite
    -0.73
    出版年
    -0.70
    writeField
    -0.64
    Maße
    -0.63
    pielt
    -0.63
     internetowa
    -0.62
    kháu
    -0.62
    Controllo
    -0.61
    POSITIVE LOGITS
     Reverso
    0.44
    nikami
    0.43
     JADX
    0.41
    TimePicker
    0.41
     decomposition
    0.40
    glDelete
    0.39
     Brasileiro
    0.39
     levanta
    0.39
    GeneratedValue
    0.39
     encapsulation
    0.38
    Activations Density 3.630%

    No Known Activations