© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3689
    Prev
    Next
    INDEX
    Explanations

    content related to the FIFA World Cup and numbers

    oai_token-act-pair · gemini-2.0-flash

    diverse specialized terms or identifiers

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

    prime factors and 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
     eight
    -0.73
     ocho
    -0.66
    8
    -0.66
     Eight
    -0.66
     four
    -0.56
     Four
    -0.56
    eight
    -0.55
    Eight
    -0.51
     oito
    -0.51
     eighth
    -0.50
    POSITIVE LOGITS
    ValueStyle
    0.96
     يتيمه
    0.84
    出版年
    0.82
    Personendaten
    0.81
     contextLoads
    0.79
    Rujuakan
    0.78
    WebVitals
    0.78
     Orrell
    0.78
    ỡng
    0.77
     cherchés
    0.75
    Activations Density 1.590%

    No Known Activations