© 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. 13914
    Prev
    Next
    INDEX
    Explanations

    mentions of administrative divisions and place names

    oai_token-act-pair · gemini-2.0-flash

    locations

    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
     Swedish
    -1.59
     Japanese
    -1.56
    Japanese
    -1.51
     Bulgarian
    -1.50
     Vietnamese
    -1.50
     Finnish
    -1.48
     Romanian
    -1.48
     Italian
    -1.48
     Portuguese
    -1.47
     Peruvian
    -1.47
    POSITIVE LOGITS
     resourceCulture
    0.80
     للمعارف
    0.70
    Viitteet
    0.69
     intptr
    0.65
     lenker
    0.60
    IContainer
    0.59
     @"/
    0.56
    Fprintf
    0.54
    참고
    0.54
    TagMode
    0.53
    Activations Density 1.650%

    No Known Activations