© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6721
    Prev
    Next
    INDEX
    Explanations

    code snippets, specifically those containing the word "Binding"

    oai_token-act-pair · gemini-2.0-flash

    Binding

    np_max-act · gemini-2.0-flash

    Binding

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     zoll
    -0.52
     ASR
    -0.52
     composta
    -0.52
     *);
    -0.52
     knji
    -0.51
     Shakspeare
    -0.50
    ContainerState
    -0.50
    =?";
    -0.50
     FSH
    -0.48
     suficiente
    -0.48
    POSITIVE LOGITS
     незавершена
    0.67
    SBATCH
    0.66
     الدولى
    0.66
    Personensuche
    0.64
     propOrder
    0.63
    بوابة
    0.62
    Lycka
    0.57
    CodeAttribute
    0.57
    ukunft
    0.56
     MemoryStream
    0.56
    Activations Density 0.999%

    No Known Activations