© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13026
    Prev
    Next
    INDEX
    Explanations

    java code syntax, especially annotations and generics

    oai_token-act-pair · gemini-2.0-flash

    multilingual terms or symbols

    np_token-act-pair-logits · gpt-4o-mini

    Java code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    ủi
    -0.56
     endregion
    -0.56
     excav
    -0.52
     bogotá
    -0.51
     dones
    -0.50
     bander
    -0.49
     elbows
    -0.48
    endregion
    -0.48
    awtextra
    -0.47
    POSITIVE LOGITS
     Référence
    0.58
    商品説明
    0.55
     Port
    0.52
    рення
    0.51
    ذت
    0.50
     Wat
    0.50
    BindingResult
    0.49
    umerable
    0.48
    اریخ
    0.48
    慑
    0.47
    Activations Density 2.044%

    No Known Activations