© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9731
    Prev
    Next
    INDEX
    Explanations

    descriptions of injuries to body parts, especially knees

    oai_token-act-pair · gemini-2.0-flash

    injuries and medicine

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    期刊论文
    -0.60
    wiec
    -0.51
    Objetivos
    -0.51
    مصادر
    -0.51
     autorytatywna
    -0.50
    ARIAN
    -0.49
    IRQn
    -0.49
    gnition
    -0.48
    lessed
    -0.48
     sil
    -0.47
    POSITIVE LOGITS
    MigrationBuilder
    0.63
     يتيمه
    0.62
    ItemLayout
    0.59
     فريبيس
    0.56
    complexType
    0.55
     judicia
    0.53
     StatelessWidget
    0.52
    CompleteListener
    0.52
     WebDriverWait
    0.51
    ValueStyle
    0.50
    Activations Density 1.305%

    No Known Activations