© 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. 11280
    Prev
    Next
    INDEX
    Explanations

    language associated with political discourse, especially involving Republicans and Democrats.

    oai_token-act-pair · gemini-2.0-flash

    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
    FirstResponder
    -0.63
    PRNewswire
    -0.63
    zzleHttp
    -0.59
     vectorielles
    -0.59
    simpleType
    -0.58
    openqa
    -0.58
    textTheme
    -0.57
     mỏng
    -0.56
    XMLSchema
    -0.56
     astore
    -0.56
    POSITIVE LOGITS
    Datuak
    0.60
    phants
    0.53
     sup
    0.51
    RegistryLite
    0.50
    stances
    0.49
     self
    0.48
     Fortune
    0.46
     Democrats
    0.46
     suppor
    0.44
    MEG
    0.44
    Activations Density 6.962%

    No Known Activations