© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11518
    Prev
    Next
    INDEX
    Explanations

    the automotive industry and the science, technology, engineering, and mathematics fields

    oai_token-act-pair · gemini-2.0-flash

    car transmissions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    tagHelper
    -0.51
     fotográfico
    -0.50
    ecutive
    -0.50
    marginHorizontal
    -0.49
     sponsorship
    -0.48
    큼
    -0.47
     withal
    -0.47
    Resumo
    -0.47
     substituted
    -0.47
    peta
    -0.46
    POSITIVE LOGITS
    parsedMessage
    0.77
    ValueStyle
    0.67
     CreateTagHelper
    0.64
    RTGC
    0.60
     متعلقه
    0.60
     دریافت‌شده
    0.59
     oprot
    0.57
    Transmission
    0.56
    UnusedPrivate
    0.56
     gainera
    0.55
    Activations Density 0.307%

    No Known Activations