© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12011
    Prev
    Next
    INDEX
    Explanations

    words/phrases related to legal or scientific investigations, processes, and documentation, sometimes mixed with seemingly unrelated common words.

    oai_token-act-pair · gemini-2.0-flash

    inquiry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     inclusive
    -0.52
    Tor
    -0.52
    Util
    -0.51
    mente
    -0.50
    inclusive
    -0.47
     Listings
    -0.46
     Tor
    -0.43
    ARGS
    -0.42
    tosh
    -0.42
     Ruling
    -0.42
    POSITIVE LOGITS
     Taktlose
    0.79
     ExecuteAsync
    0.76
    bewerken
    0.69
     الرياضيه
    0.67
    Personensuche
    0.66
     Wikimedijinoj
    0.65
     typelib
    0.62
    _));
    0.61
    lebo
    0.60
    :✨
    0.59
    Activations Density 7.157%

    No Known Activations