© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14293
    Prev
    Next
    INDEX
    Explanations

    figure references and numerical data

    oai_token-act-pair · gemini-2.0-flash

    technical terms or identifiers in code

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

    Figures and diagrams

    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
    RenderAtEndOf
    -0.52
    agrave
    -0.51
     BS
    -0.47
     cherchés
    -0.47
    RunAsync
    -0.45
     bs
    -0.45
    intendo
    -0.43
     ||=
    -0.43
    UnknownFields
    -0.42
    bs
    -0.42
    POSITIVE LOGITS
    uxxxx
    0.80
    FXML
    0.66
     électroniques
    0.65
    AccessorTable
    0.64
     condamné
    0.63
    MethodManager
    0.62
     חיצוניים
    0.59
    Wyd
    0.57
     ouest
    0.56
     coelho
    0.56
    Activations Density 2.818%

    No Known Activations