© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5032
    Prev
    Next
    INDEX
    Explanations

    C++ code related to 3D vectors

    oai_token-act-pair · gemini-2.0-flash

    class and code structure identifiers

    np_token-act-pair-logits · gpt-4o-mini

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     المعيارى
    -0.65
    ReusableCell
    -0.63
     الرياضيه
    -0.61
    breathe
    -0.57
    SharedDtor
    -0.57
    ThemeOverlay
    -0.57
    gnore
    -0.55
     myſelf
    -0.54
    Açık
    -0.54
    autom
    -0.52
    POSITIVE LOGITS
     Mada
    0.49
    World
    0.48
     World
    0.47
    WebElementEntity
    0.46
    Object
    0.44
    up
    0.43
    вър
    0.43
    lllllllll
    0.43
     e
    0.42
    Up
    0.42
    Activations Density 6.782%

    No Known Activations