© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5448
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to quantity, time, or measurements

    oai_token-act-pair · gemini-2.0-flash

    numbers, specifically counting

    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
    -0.89
     Approximately
    -0.83
     approx
    -0.80
     約
    -0.79
    约
    -0.79
    Approximately
    -0.78
     roughly
    -0.75
    約
    -0.75
     aproximadamente
    -0.69
    approximately
    -0.69
    POSITIVE LOGITS
     four
    1.13
     six
    1.12
     three
    1.09
     seven
    1.09
    three
    1.02
    six
    1.01
     eight
    1.00
     five
    0.99
    four
    0.99
     FOUR
    0.98
    Activations Density 4.174%

    No Known Activations