© 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. 3037
    Prev
    Next
    INDEX
    Explanations

    information about trails including their names, lengths, and locations

    oai_token-act-pair · gemini-2.0-flash

    trails and networks

    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
    Biographie
    -0.54
    WithIOException
    -0.53
     Wallflower
    -0.53
    chevêque
    -0.52
     beziehen
    -0.51
    addContainerGap
    -0.49
     ControllerBase
    -0.49
     belong
    -0.47
     AssemblyCulture
    -0.45
    ++];
    -0.45
    POSITIVE LOGITS
     estimés
    0.57
    Jereo
    0.53
    actéristique
    0.53
     numerus
    0.52
     Wikimedijinoj
    0.52
    Companion
    0.50
     taping
    0.50
    ObjectMeta
    0.48
    NameInMap
    0.48
    étro
    0.47
    Activations Density 2.855%

    No Known Activations