© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4704
    Prev
    Next
    INDEX
    Explanations

    words related to sports teams, locations, and future actions

    oai_token-act-pair · gemini-2.0-flash

    Sports news/announcements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     AssemblyCulture
    -0.57
    TypedDataSet
    -0.56
    IUrlHelper
    -0.55
     Head
    -0.53
     sumpay
    -0.52
     Winaray
    -0.51
    Head
    -0.51
     kasarigan
    -0.50
    المناصب
    -0.50
     ModelExpression
    -0.49
    POSITIVE LOGITS
    
    0.94
     préfé
    0.59
    LogFactory
    0.56
    ligente
    0.54
     Menor
    0.51
    CrossRef
    0.50
    CSRF
    0.49
    tonode
    0.49
     contes
    0.48
    是非
    0.47
    Activations Density 4.854%

    No Known Activations