© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15621
    Prev
    Next
    INDEX
    Explanations

    proper nouns that are people's names, especially politicians, and other terms related to elections

    oai_token-act-pair · gemini-2.0-flash

    US Politics

    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
     chúc
    -0.45
     Theron
    -0.44
    uresh
    -0.43
    стал
    -0.42
    atillas
    -0.42
    Références
    -0.41
     Terminal
    -0.40
    غب
    -0.40
    انس
    -0.39
    としての
    -0.39
    POSITIVE LOGITS
     للاسماء
    0.88
    aarrggbb
    0.86
    Бахар
    0.78
    PreferredItem
    0.73
    HasForeignKey
    0.66
    mergeFrom
    0.65
    ########.
    0.64
    GraphicsUnit
    0.64
    uxxxx
    0.64
     ویکی‌پدیای
    0.62
    Activations Density 1.307%

    No Known Activations