© 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. 5830
    Prev
    Next
    INDEX
    Explanations

    references to locations, particularly in India

    oai_token-act-pair · gemini-2.0-flash

    Indian

    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
     Indian
    -1.88
    Indian
    -1.70
     India
    -1.66
    India
    -1.58
     indian
    -1.57
     INDIAN
    -1.54
     Indians
    -1.43
     india
    -1.37
     INDIA
    -1.36
    indian
    -1.28
    POSITIVE LOGITS
     @"/
    0.53
    Vedi
    0.50
     Censo
    0.48
    ніципалі
    0.46
     ProtoMessage
    0.45
    toMatch
    0.45
    ControllerAdvice
    0.44
    ///</
    0.42
    شود
    0.42
    Ран
    0.42
    Activations Density 0.706%

    No Known Activations