© 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. 14114
    Prev
    Next
    INDEX
    Explanations

    location names, especially from India, and words relating to government and politics.

    oai_token-act-pair · gemini-2.0-flash

    India

    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
    -1.71
     India
    -1.65
    Indian
    -1.59
    India
    -1.49
     indian
    -1.45
     Indians
    -1.38
     INDIAN
    -1.35
     india
    -1.27
    indian
    -1.26
    india
    -1.24
    POSITIVE LOGITS
    enumi
    0.66
     Pakistan
    0.55
    GEBURTS
    0.54
    padek
    0.52
     surla
    0.52
     متعلقه
    0.50
     sguardo
    0.49
     AssemblyTitle
    0.49
     Pakistani
    0.47
    Pakistan
    0.47
    Activations Density 3.599%

    No Known Activations