© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11686
    Prev
    Next
    INDEX
    Explanations

    code related to matching, potentially in testing contexts

    oai_token-act-pair · gemini-2.0-flash

    mock

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    InputBorder
    -0.96
     onAnimation
    -0.90
    sidemargin
    -0.87
     useHistory
    -0.81
     GIPHY
    -0.81
    ymce
    -0.79
    ViewImports
    -0.79
    TypedDataSet
    -0.75
    ChildScrollView
    -0.75
    extAlignment
    -0.75
    POSITIVE LOGITS
    <bos>
    0.89
    ↵↵
    0.50
    ↵
    0.49
     the
    0.47
    MigrationBuilder
    0.46
    Sub
    0.46
    2
    0.45
    <em>
    0.45
    Plan
    0.44
    /**
    0.43
    Activations Density 0.664%

    No Known Activations