© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5969
    Prev
    Next
    INDEX
    Explanations

    terms used to describe broadcasting live news from a remote location back to the newsroom

    oai_token-act-pair · gemini-2.0-flash

    network connection

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    PreferredItem
    -0.71
     مشين
    -0.66
    #+#
    -0.65
     ModelAndView
    -0.63
     NgModule
    -0.63
    SharedCtor
    -0.60
     disambiguazione
    -0.59
     propOrder
    -0.57
    apimachinery
    -0.55
     himo
    -0.54
    POSITIVE LOGITS
     connection
    1.63
     communication
    1.39
     connect
    1.37
    connection
    1.34
     connections
    1.34
     Connection
    1.31
     communications
    1.27
     connexion
    1.22
    Connection
    1.20
     connecting
    1.20
    Activations Density 2.818%

    No Known Activations