© 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. 7260
    Prev
    Next
    INDEX
    Explanations

    code syntax for declaring functions, beginning blocks, ending blocks, and declaring variables

    oai_token-act-pair · gemini-2.0-flash

    begin

    np_max-act · gemini-2.0-flash
    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
     InputDecoration
    -0.87
    BackStack
    -0.71
    ‚¬
    -0.70
    argout
    -0.66
    TypedDataSet
    -0.65
     تانيه
    -0.65
    awtextra
    -0.64
    ymce
    -0.63
     BoxDecoration
    -0.63
    <bos>
    -0.63
    POSITIVE LOGITS
     kasarigan
    0.59
    RegressionTest
    0.54
     Roskov
    0.52
    __':
    0.50
     ویکی‌پدی
    0.49
    __':
    0.48
    eraard
    0.48
    calientes
    0.47
    uteurs
    0.45
     priorité
    0.45
    Activations Density 0.824%

    No Known Activations