© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10571
    Prev
    Next
    INDEX
    Explanations

    HTML, Tax code, Gene and chemical nomenclature.

    oai_token-act-pair · gemini-2.0-flash

    try

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    UTO
    -0.71
    دانشنامهٔ
    -0.65
    migrationBuilder
    -0.64
     propOrder
    -0.64
    sto
    -0.62
    IBIL
    -0.62
    usermodel
    -0.62
    STO
    -0.62
    TO
    -0.60
    Sto
    -0.59
    POSITIVE LOGITS
    try
    0.84
     tries
    0.82
     try
    0.82
    tries
    0.66
    Try
    0.64
     tried
    0.60
     Tries
    0.60
     trying
    0.57
     Try
    0.56
    TRY
    0.56
    Activations Density 1.904%

    No Known Activations