© 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. 4419
    Prev
    Next
    INDEX
    Explanations

    text relating to Brazilian politics, corruption, and legal proceedings.

    oai_token-act-pair · gemini-2.0-flash

    coding or programming terminology

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

    Prepositions and articles

    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
    клопе
    -0.71
    OrBuilder
    -0.64
     الرياضيه
    -0.62
    таратура
    -0.62
     EconPapers
    -0.62
    (;;)
    -0.61
    पया
    -0.57
    ativement
    -0.57
    μον
    -0.55
    PerformLayout
    -0.55
    POSITIVE LOGITS
     AssemblyProduct
    0.51
    截
    0.46
    index
    0.46
    int
    0.45
    geen
    0.45
     截
    0.41
     CreateTagHelper
    0.41
    templateUrl
    0.40
     تضيفلها
    0.40
    有一天
    0.40
    Activations Density 0.936%

    No Known Activations