© 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. 6774
    Prev
    Next
    INDEX
    Explanations

    apostrophes, especially in contractions (like "I'm," "don't," or "it's") and quotation marks

    oai_token-act-pair · 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
     Wiktionnaire
    -0.95
    niająca
    -0.69
    addGap
    -0.68
    ADELPHIA
    -0.68
    (_,
    -0.66
    "?>
    -0.66
    awtextra
    -0.64
    
    -0.63
     propOrder
    -0.63
    BASEPATH
    -0.63
    POSITIVE LOGITS
    WireFormat
    0.52
    __':
    0.46
     publiek
    0.45
     vérit
    0.44
     blanches
    0.44
     selera
    0.43
     savez
    0.42
     trock
    0.42
     contemporaine
    0.42
     felb
    0.41
    Activations Density 0.214%

    No Known Activations