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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2904
    Prev
    Next
    INDEX
    Explanations

    code snippets with formatting characters and some i2c-related C code

    oai_token-act-pair · gemini-2.0-flash

    code snippets/mathematical expressions

    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
    dryer
    -0.54
    tvguidetime
    -0.52
    شهاد
    -0.49
    מבר
    -0.48
    Kanpo
    -0.47
    Unmarshaller
    -0.46
    ällä
    -0.45
    WritableDatabase
    -0.45
    HORIZONTAL
    -0.44
    Statistiche
    -0.44
    POSITIVE LOGITS
    WindowConstants
    0.72
    WithIOException
    0.68
     فريبيس
    0.68
    AndEndTag
    0.66
    ItemBackground
    0.60
    InjectAttribute
    0.59
     Мексичка
    0.58
    //</
    0.58
     مشين
    0.55
    reportWebVitals
    0.55
    Activations Density 6.611%

    No Known Activations