© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5516
    Prev
    Next
    INDEX
    Explanations

    technical or parenthetical language and the words "time" and "random"

    oai_token-act-pair · gemini-2.0-flash

    Acronyms and initialisms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     badan
    -0.45
    Rüyada
    -0.44
    wezen
    -0.44
    JsonFormat
    -0.44
    ⓧ
    -0.41
    CUIT
    -0.41
    SWT
    -0.40
    kolog
    -0.40
    Autoritní
    -0.40
     bort
    -0.40
    POSITIVE LOGITS
    aarrggbb
    0.72
    WebElementEntity
    0.70
    ThroughAttribute
    0.65
    ttino
    0.65
     trillion
    0.58
    Tra
    0.57
    technical
    0.57
    thomas
    0.57
    testng
    0.57
     tooth
    0.57
    Activations Density 4.195%

    No Known Activations