© 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. 10889
    Prev
    Next
    INDEX
    Explanations

    place names

    oai_token-act-pair · 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
     ExecuteAsync
    -0.83
     الحره
    -0.77
    abestanden
    -0.73
     useStyles
    -0.73
     CommonModule
    -0.72
     propOrder
    -0.72
    ^(@)
    -0.72
    Obrázky
    -0.71
     initComponents
    -0.71
    Становништво
    -0.68
    POSITIVE LOGITS
    FormTagHelper
    0.39
     Her
    0.39
     sod
    0.36
     gest
    0.35
    Her
    0.34
     ged
    0.33
     `
    0.33
    w
    0.33
    правля
    0.33
     Su
    0.33
    Activations Density 0.166%

    No Known Activations