© 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. 4947
    Prev
    Next
    INDEX
    Explanations

    terms related to clinical trials and medical treatments

    oai_token-act-pair · gemini-2.0-flash

    words related to usage and consumption

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

    Related to "use"

    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
    ittar
    -0.42
    nvidia
    -0.39
    canti
    -0.38
     landet
    -0.38
    ുടെ
    -0.37
    onar
    -0.37
    pDialog
    -0.37
    illers
    -0.37
    OrBuilder
    -0.36
    وامل
    -0.36
    POSITIVE LOGITS
     use
    1.34
     usage
    1.26
     consumption
    1.13
     utilisation
    1.09
     utilization
    1.07
     gebruik
    1.00
    usage
    0.98
     implementation
    0.95
     participation
    0.95
     ownership
    0.95
    Activations Density 7.561%

    No Known Activations