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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2462
    Prev
    Next
    INDEX
    Explanations

    names of people and organizations, particularly those involved in US politics

    oai_token-act-pair · gemini-2.0-flash

    Trump

    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
     Trump
    -0.92
     propOrder
    -0.90
    Trump
    -0.86
    Rhestr
    -0.75
     trump
    -0.74
    Бахар
    -0.73
     Donald
    -0.71
     الرياضيه
    -0.70
    antism
    -0.70
    HostException
    -0.70
    POSITIVE LOGITS
     consciência
    0.48
     immédi
    0.43
     vone
    0.41
    الإنجليزية
    0.41
     professionali
    0.41
     supérieurs
    0.41
     veckor
    0.39
    添
    0.39
     inuti
    0.38
     strictement
    0.38
    Activations Density 10.723%

    No Known Activations