© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5526
    Prev
    Next
    INDEX
    Explanations

    mentions of numbers or numerical data

    oai_token-act-pair · gemini-2.0-flash

    Seven

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    5
    -0.77
    4
    -0.73
    fifths
    -0.61
     five
    -0.60
     fifth
    -0.60
    ⁵
    -0.60
     cinque
    -0.60
     Five
    -0.59
    five
    -0.58
    ৪
    -0.57
    POSITIVE LOGITS
     Seven
    1.00
     seventh
    0.98
     Seventh
    0.95
     seven
    0.94
    Seven
    0.88
    7
    0.87
    Seventh
    0.82
    七
    0.81
     SEVEN
    0.81
    seven
    0.77
    Activations Density 1.746%

    No Known Activations