© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2481
    Prev
    Next
    INDEX
    Explanations

    code artifacts, such as specific symbols or comments

    oai_token-act-pair · gemini-2.0-flash

    ref

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    RegressionTest
    -1.03
    findpost
    -1.02
    IntoConstraints
    -0.93
    ConstraintMaker
    -0.84
     resourceCulture
    -0.82
    FormTagHelper
    -0.79
    httphttps
    -0.78
    AddHtmlAttribute
    -0.77
    styleType
    -0.77
     otomatig
    -0.77
    POSITIVE LOGITS
     køb
    0.47
     mecánico
    0.43
    บุรี
    0.42
     canadien
    0.41
     peixes
    0.41
     folha
    0.40
    in
    0.40
     amargo
    0.40
    <strong>
    0.40
     ديسمبر
    0.39
    Activations Density 0.454%

    No Known Activations