© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11004
    Prev
    Next
    INDEX
    Explanations

    mentions of governments or parties

    oai_token-act-pair · gemini-2.0-flash

    government

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     avoient
    -0.81
    bootstrapcdn
    -0.81
     bénévoles
    -0.72
     positifs
    -0.70
     étoient
    -0.69
     juges
    -0.68
     dieux
    -0.66
    RegressionTest
    -0.66
     chré
    -0.66
    mybatisplus
    -0.65
    POSITIVE LOGITS
    ">—
    0.53
    XmlAccessType
    0.45
    مصادر
    0.43
    poco
    0.40
    一行
    0.40
     torno
    0.39
     intptr
    0.39
     affairs
    0.38
     tung
    0.38
     متعلقه
    0.38
    Activations Density 0.853%

    No Known Activations