© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8484
    Prev
    Next
    INDEX
    Explanations

    statistics and numerical information within a text

    oai_token-act-pair · gemini-2.0-flash

    numbers related to statistics or estimates

    np_token-act-pair-logits · gpt-4o-mini

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     approximately
    -1.16
    Approximately
    -1.16
     Approximately
    -1.15
    approximately
    -0.98
     aproximadamente
    -0.92
     roughly
    -0.90
     Approx
    -0.90
    Nearly
    -0.89
     approx
    -0.89
     約
    -0.87
    POSITIVE LOGITS
     half
    0.78
     
    0.70
     thirty
    0.68
     five
    0.68
     twenty
    0.68
     fifteen
    0.67
     ten
    0.67
    half
    0.64
     halv
    0.62
     seven
    0.61
    Activations Density 2.771%

    No Known Activations