© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14348
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the US government and its interaction with Russia

    oai_token-act-pair · gemini-2.0-flash

    names and terms related to current events and politics

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

    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_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
     http
    -0.63
    http
    -0.55
     Obama
    -0.50
    Obama
    -0.43
     blog
    -0.43
     Zika
    -0.43
    ecake
    -0.42
    ColumnHeaders
    -0.42
    blog
    -0.41
     xrange
    -0.40
    POSITIVE LOGITS
     Biden
    1.09
    ArgsConstructor
    1.02
    Biden
    0.94
     '\\;'
    0.94
    webElementXpaths
    0.93
     TikTok
    0.91
     pandemic
    0.91
    DockStyle
    0.90
    TikTok
    0.85
    pandemic
    0.83
    Activations Density 1.428%

    No Known Activations