© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12717
    Prev
    Next
    INDEX
    Explanations

    words related to politics, laws, and policies

    oai_token-act-pair · gemini-2.0-flash

    Law and politics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Personendaten
    -0.57
    AddHtmlAttribute
    -0.55
    <bos>
    -0.52
     AssemblyProduct
    -0.52
    liflower
    -0.51
    oneofs
    -0.49
     Meksiku
    -0.48
    rungsseite
    -0.47
    ⓧ
    -0.47
    GEBURTS
    -0.46
    POSITIVE LOGITS
    ATEGORIES
    0.59
    ftant
    0.58
    CompleteListener
    0.55
     contextLoads
    0.54
    ondern
    0.54
    gorithm
    0.54
    לום
    0.53
     Tampoco
    0.52
     CHAPITRE
    0.52
     tabindex
    0.52
    Activations Density 1.864%

    No Known Activations