© 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. 6388
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with political discourse, deal making, and constitutional issues.

    oai_token-act-pair · gemini-2.0-flash

    political commentary

    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
    URIComponent
    -0.47
     propOrder
    -0.46
    TAKT
    -0.44
    NameInMap
    -0.44
     pié
    -0.44
    cillors
    -0.43
    QtWidgets
    -0.43
    доб
    -0.43
    ili
    -0.43
    RegistryLite
    -0.42
    POSITIVE LOGITS
    ⓧ
    0.70
     resourceCulture
    0.57
     $_"
    0.57
     protoimpl
    0.56
    breviations
    0.56
    TestingModule
    0.54
    Spoljašnje
    0.54
    airbnb
    0.54
     Мексичка
    0.54
    MemoryWarning
    0.54
    Activations Density 7.341%

    No Known Activations