© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6845
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to US politics, especially events surrounding the 2016 election and Russia.

    oai_token-act-pair · gemini-2.0-flash

    filtered legislative terms

    np_token-act-pair-logits · gpt-4o-mini

    House/Senate

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    RectangleBorder
    -1.02
    ValueStyle
    -0.92
     CommonModule
    -0.85
     disambiguazione
    -0.79
    TagHelper
    -0.71
     JpaRepository
    -0.69
    npos
    -0.65
    SourceChecksum
    -0.63
     répondit
    -0.62
    AddTagHelper
    -0.61
    POSITIVE LOGITS
     uska
    0.58
    Bad
    0.47
     page
    0.45
     ren
    0.45
    chat
    0.43
     cha
    0.43
     d
    0.43
    d
    0.43
     chat
    0.42
     Bad
    0.42
    Activations Density 0.952%

    No Known Activations