© 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. 8342
    Prev
    Next
    INDEX
    Explanations

    numbers and currency symbols, and sometimes words like "for" and "in" that come before or after the numbers

    oai_token-act-pair · gemini-2.0-flash

    numerical values or quantities

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

    Numbers as words

    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
     CreateTagHelper
    -1.65
     للمعارف
    -1.40
    ItemBackground
    -1.35
    :✨
    -1.20
     transfieras
    -1.19
    بوابة
    -1.16
     يتيمه
    -1.14
     itſelf
    -1.13
     iſt
    -1.12
    AddTagHelper
    -1.12
    POSITIVE LOGITS
     two
    1.13
     three
    1.07
     four
    1.03
     six
    0.88
     five
    0.84
     quatro
    0.80
    two
    0.80
     trois
    0.79
    three
    0.79
     deux
    0.78
    Activations Density 2.048%

    No Known Activations