© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12383
    Prev
    Next
    INDEX
    Explanations

    AWS related terms, particularly for the Kinesis and Firehose services, inside of code examples

    oai_token-act-pair · gemini-2.0-flash

    aws

    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
     purpoſe
    -0.76
     FetchType
    -0.72
    CloseOperation
    -0.72
     pleaſure
    -0.72
    QtCore
    -0.71
    ContentAsync
    -0.70
    ostar
    -0.69
    QtWidgets
    -0.66
     houſe
    -0.66
     Freuden
    -0.65
    POSITIVE LOGITS
     ComVisible
    0.62
     فريبيس
    0.52
    CPtr
    0.47
    fjspx
    0.47
    PreferredItem
    0.47
     disambiguazione
    0.46
    SharedDtor
    0.45
    UnknownFieldSet
    0.44
    AutoField
    0.43
    protoimpl
    0.43
    Activations Density 1.325%

    No Known Activations