© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1974
    Prev
    Next
    INDEX
    Explanations

    code syntax, programming keywords, and file paths

    oai_token-act-pair · gemini-2.0-flash

    Code

    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
    TagHelper
    -0.57
    Acc
    -0.49
    ọa
    -0.49
    <bos>
    -0.47
    sequelize
    -0.45
     /^\
    -0.45
    isNameExpr
    -0.43
    ifred
    -0.43
    umą
    -0.42
    celia
    -0.42
    POSITIVE LOGITS
    دانشنامهٔ
    0.81
    InjectAttribute
    0.73
    sizeCache
    0.73
    хьтан
    0.73
     '\\;'
    0.72
    AddHtmlAttribute
    0.71
     protoimpl
    0.71
    GEBURTSDATUM
    0.71
    hoeddwyd
    0.71
    IonicModule
    0.71
    Activations Density 86.594%

    No Known Activations