© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12614
    Prev
    Next
    INDEX
    Explanations

    words related to Oregon and specific organizations mostly located there but also some general locations

    oai_token-act-pair · gemini-2.0-flash

    Pacific region

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Seattle
    -1.36
    Seattle
    -1.34
     Oregon
    -1.31
     Portland
    -1.30
     OREGON
    -1.27
    Oregon
    -1.25
     PACIFIC
    -1.23
     Pacific
    -1.23
    Portland
    -1.20
    Pacific
    -1.13
    POSITIVE LOGITS
    rungsseite
    0.54
    expandindo
    0.53
     разу
    0.49
     dispara
    0.48
    DPI
    0.48
    olus
    0.46
     Alves
    0.45
     davon
    0.41
    Guerra
    0.41
    voi
    0.40
    Activations Density 1.770%

    No Known Activations