© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14549
    Prev
    Next
    INDEX
    Explanations

    locations and geographic entities such as regions, states, and countries

    oai_token-act-pair · 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
     FL
    -1.77
     Florida
    -1.71
     Flu
    -1.66
     Fl
    -1.64
     flu
    -1.63
     Fla
    -1.62
    flu
    -1.59
    Florida
    -1.59
    Flu
    -1.57
     Flor
    -1.55
    POSITIVE LOGITS
    visející
    0.55
    uberge
    0.53
     Edelman
    0.50
     Rodin
    0.50
     Jonny
    0.48
     nướng
    0.48
    nordic
    0.47
     cabra
    0.46
    ječ
    0.46
     Samo
    0.45
    Activations Density 1.546%

    No Known Activations