© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10183
    Prev
    Next
    INDEX
    Explanations

    words, letters, and phrases used in technical and scientific writing with a variety of different contexts.

    oai_token-act-pair · gemini-2.0-flash

    business, politics, law

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    featureID
    -0.78
    AddTagHelper
    -0.75
     typelib
    -0.71
     AssemblyCulture
    -0.70
    archiviato
    -0.68
    IndentedString
    -0.68
    EDEFAULT
    -0.67
     GDR
    -0.67
     Мексичка
    -0.66
     Athenians
    -0.66
    POSITIVE LOGITS
    фика
    0.55
    setFrame
    0.52
    ulator
    0.47
     kons
    0.44
    enso
    0.43
    jut
    0.43
    Excerpt
    0.43
    :
    0.43
    mite
    0.43
    copia
    0.42
    Activations Density 5.833%

    No Known Activations