© 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. 10806
    Prev
    Next
    INDEX
    Explanations

    references to items being shown or discussed "below".

    oai_token-act-pair · gemini-2.0-flash

    phrases indicating content or questions to follow

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

    below

    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
    UnknownFieldSet
    -0.73
    webElementXpaths
    -0.71
    uisine
    -0.60
    Демографія
    -0.60
    MigrationBuilder
    -0.56
    SourceChecksum
    -0.54
     Stodd
    -0.54
    Попис
    -0.54
    etcode
    -0.52
    ItemBackground
    -0.51
    POSITIVE LOGITS
     RIPRODUZIONE
    0.55
     wireType
    0.52
    FTFY
    0.51
     Arhi
    0.51
    بوابة
    0.51
    :✨
    0.48
     незавершена
    0.47
     fiducia
    0.47
    érêt
    0.47
    brać
    0.47
    Activations Density 7.919%

    No Known Activations