© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6669
    Prev
    Next
    INDEX
    Explanations

    the names of cities and countries, especially in the context of offices

    oai_token-act-pair · gemini-2.0-flash

    office 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_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     adipis
    -0.57
    __((
    -0.50
    eward
    -0.49
    MemoryWarning
    -0.47
    FunctionFlags
    -0.47
    weetened
    -0.46
    uname
    -0.46
     Sinne
    -0.46
    ânsito
    -0.46
    vierung
    -0.46
    POSITIVE LOGITS
     office
    1.21
     chapter
    1.09
     offices
    1.08
     chapters
    1.03
     OFFICE
    1.02
    office
    1.02
     Chapter
    0.98
    chapter
    0.97
     branch
    0.96
     Office
    0.93
    Activations Density 0.747%

    No Known Activations