© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12127
    Prev
    Next
    INDEX
    Explanations

    occurrences of the digit 1 followed by another digit

    oai_token-act-pair · gemini-2.0-flash

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    tvguidetime
    -0.78
    DeleteBehavior
    -0.75
     AssemblyCulture
    -0.72
    
    -0.70
    WebElementEntity
    -0.70
     Paglinawan
    -0.70
     betweenstory
    -0.68
     "..\..\..\
    -0.67
    Bronnen
    -0.66
    MemoryWarning
    -0.65
    POSITIVE LOGITS
    <bos>
    0.97
    One
    0.60
     one
    0.56
     One
    0.54
    __':
    0.50
     gång
    0.50
    šanai
    0.49
     teken
    0.48
    __":
    0.47
    有一個
    0.46
    Activations Density 0.548%

    No Known Activations