© 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. 3835
    Prev
    Next
    INDEX
    Explanations

    references to subdistricts and towns in China

    oai_token-act-pair · gemini-2.0-flash

    (

    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
     Efq
    -0.80
     Majefty
    -0.75
     contextLoads
    -0.66
     Theſe
    -0.65
     themſelves
    -0.60
     reaſon
    -0.59
     pleaſure
    -0.59
     whoſe
    -0.59
     purpoſe
    -0.59
     myſelf
    -0.57
    POSITIVE LOGITS
    台中
    0.78
    ThroughAttribute
    0.74
    云南
    0.73
    Botswana
    0.73
    台南
    0.71
    Rhode
    0.70
    福建
    0.70
    Alberta
    0.69
    Nebraska
    0.68
     pulumi
    0.68
    Activations Density 1.154%

    No Known Activations