© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5925
    Prev
    Next
    INDEX
    Explanations

    references to the town of Ballymena, Irish people, and other names related to Ireland and its history

    oai_token-act-pair · gemini-2.0-flash

    Ballymena

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    StoryboardSegue
    -0.69
    <?
    -0.68
    
    -0.66
     pleaſure
    -0.62
     himſelf
    -0.59
    utí
    -0.57
     Jefus
    -0.57
    isDebugEnabled
    -0.57
    IsMutable
    -0.56
     themſelves
    -0.56
    POSITIVE LOGITS
     estimés
    0.62
    Tikang
    0.60
    álja
    0.56
    ukone
    0.54
     gepubliceerd
    0.48
    pidou
    0.48
    QMetaType
    0.47
     henvisninger
    0.46
    出版年
    0.46
     نمایید
    0.44
    Activations Density 0.404%

    No Known Activations