© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4237
    Prev
    Next
    INDEX
    Explanations

    words inside tables describing a project or process requiring intervention and action

    oai_token-act-pair · gemini-2.0-flash

    Data tables

    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
    ConstraintMaker
    -0.57
    SuspendLayout
    -0.52
     Consultado
    -0.50
    moins
    -0.49
     poveznice
    -0.48
     ddelweddau
    -0.47
     resourceCulture
    -0.47
    دانشنامهٔ
    -0.46
     cherchés
    -0.45
     autorytatywna
    -0.44
    POSITIVE LOGITS
    QMetaType
    0.72
     متعلقه
    0.72
    __*/
    0.67
    ///</
    0.65
    PreferredItem
    0.64
     }{@
    0.62
     AssemblyTitle
    0.62
    >>()
    0.62
    тинга
    0.60
    ">+
    0.60
    Activations Density 3.856%

    No Known Activations