© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14639
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical areas, especially when discussing sports

    oai_token-act-pair · gemini-2.0-flash

    zone

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     zone
    -1.80
     Zone
    -1.77
    zone
    -1.67
     ZONE
    -1.66
    Zone
    -1.66
     zones
    -1.61
     Zones
    -1.57
    ZONE
    -1.45
    zones
    -1.45
    Zones
    -1.30
    POSITIVE LOGITS
     פר
    0.47
     šte
    0.46
    fattning
    0.45
    zydent
    0.45
     corto
    0.44
    續
    0.43
     ces
    0.42
     Ar
    0.42
    gin
    0.42
     par
    0.42
    Activations Density 7.865%

    No Known Activations