© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13869
    Prev
    Next
    INDEX
    Explanations

    a description of a neural network that contains the words and ideas "input", "output", "layer", "network", and "nodes"

    oai_token-act-pair · gemini-2.0-flash

    neural networks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    IntoConstraints
    -0.69
    TestingModule
    -0.65
     ffilmiau
    -0.60
    WriteTagHelper
    -0.54
     AssemblyVersion
    -0.52
     >=",
    -0.52
    onnay
    -0.51
    ViewImports
    -0.48
     zyn
    -0.46
     Rayleigh
    -0.46
    POSITIVE LOGITS
     تانيه
    0.58
     cherchés
    0.56
    GEBURTS
    0.56
    twimg
    0.54
     odkazy
    0.52
    bringer
    0.49
    vantaged
    0.49
    AddHtmlAttribute
    0.48
    Vanjske
    0.47
     szí
    0.47
    Activations Density 3.234%

    No Known Activations