© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5298
    Prev
    Next
    INDEX
    Explanations

    biochemical terms related to cell signaling pathways and protein expression

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms

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

    biological signaling pathways

    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
    IsContent
    -0.79
     Paglinawan
    -0.66
    getDoctrine
    -0.64
    UserScript
    -0.61
     Jefus
    -0.61
     nakalista
    -0.60
     Chriftian
    -0.59
     estekak
    -0.59
     pleaſure
    -0.59
     Cæsar
    -0.59
    POSITIVE LOGITS
    StructEnd
    0.49
    __(/*!
    0.45
     Lot
    0.45
    Lot
    0.41
    elum
    0.41
     Lottie
    0.40
    unton
    0.39
    RequestBuilder
    0.39
    Kontakt
    0.38
     Contactez
    0.38
    Activations Density 2.460%

    No Known Activations