© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6472
    Prev
    Next
    INDEX
    Explanations

    terms used in government and politics

    oai_token-act-pair · gemini-2.0-flash

    Government leader title

    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
     President
    -0.68
    President
    -0.68
     presidents
    -0.67
     president
    -0.67
    president
    -0.65
     Presidents
    -0.65
     Präsident
    -0.59
    Presidents
    -0.56
     PRESIDENT
    -0.55
    Presidente
    -0.54
    POSITIVE LOGITS
     minister
    1.41
     Prime
    1.36
     Minister
    1.35
    Minister
    1.32
    minister
    1.27
    Prime
    1.22
     ministers
    1.17
     prime
    1.17
     Ministers
    1.15
     MINISTER
    1.13
    Activations Density 2.399%

    No Known Activations