© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15249
    Prev
    Next
    INDEX
    Explanations

    words related to current events, statistics, and news

    oai_token-act-pair · gemini-2.0-flash

    economic and health crisis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    vää
    -0.51
     crisis
    -0.45
     CreateTagHelper
    -0.45
     bang
    -0.42
    CENTER
    -0.42
     note
    -0.40
    crisis
    -0.39
     chính
    -0.38
     gero
    -0.38
     хо
    -0.37
    POSITIVE LOGITS
    RenderAtEndOf
    0.85
    sidemargin
    0.83
    elemField
    0.82
     يتيمه
    0.80
    TagMode
    0.80
    :✨
    0.78
     uintptr
    0.78
     ModelExpression
    0.77
    NgModule
    0.73
    ArgumentParser
    0.73
    Activations Density 43.742%

    No Known Activations