© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8672
    Prev
    Next
    INDEX
    Explanations

    text related to the clinical testing and commercialization of pharmaceutical products

    oai_token-act-pair · gemini-2.0-flash

    izing, ize, testing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    CloseOperation
    -0.70
    AndEndTag
    -0.65
    ंदीखरीदारी
    -0.59
    اریخ
    -0.59
     Pristupljeno
    -0.58
    UpInside
    -0.58
     saites
    -0.57
    enties
    -0.55
    انيف
    -0.55
    ыгана
    -0.54
    POSITIVE LOGITS
    tvguidetime
    0.68
    UnknownFieldSet
    0.53
    WebServlet
    0.52
     Flur
    0.51
    __()
    0.51
    ::<
    0.50
    oplayer
    0.50
     hiểm
    0.50
     valueForKey
    0.49
    pherals
    0.49
    Activations Density 2.927%

    No Known Activations