© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10660
    Prev
    Next
    INDEX
    Explanations

    mentions of European places and institutions, especially in the context of professional titles and affiliations

    oai_token-act-pair · gemini-2.0-flash

    Kentucky locations and routes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Belgian
    -1.15
     Belgi
    -1.02
     Belgium
    -0.97
    Belgian
    -0.91
     Dutch
    -0.86
     belg
    -0.85
     belga
    -0.83
    Belgium
    -0.81
     Netherlands
    -0.80
     Belgische
    -0.80
    POSITIVE LOGITS
    WebVitals
    0.71
    awtextra
    0.64
    matchCondition
    0.63
    WithMany
    0.56
    AddTagHelper
    0.56
    LayoutStyle
    0.55
     useRef
    0.55
    UnsafeEnabled
    0.54
    ViewImports
    0.53
    IsContent
    0.52
    Activations Density 0.941%

    No Known Activations