© 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. 12-GEMMASCOPE-TRANSCODER-16K
    4. 12954
    Prev
    Next
    INDEX
    Explanations

    LaTeX math mode symbols and equations.

    oai_token-act-pair · gemini-2.0-flash

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     pièce
    -0.44
     Horacio
    -0.44
     gostar
    -0.44
     ISNI
    -0.44
     necesar
    -0.43
    idin
    -0.43
    ebilir
    -0.42
     thereon
    -0.41
     pector
    -0.41
    lehre
    -0.41
    POSITIVE LOGITS
    tagHelperRunner
    0.82
    UnsafeEnabled
    0.79
     kasarigan
    0.77
    
    0.73
    WindowConstants
    0.70
     surla
    0.68
    ंदीखरीदारी
    0.68
     oprot
    0.63
     חיצוניים
    0.61
     링크
    0.61
    Activations Density 1.156%

    No Known Activations