© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11769
    Prev
    Next
    INDEX
    Explanations

    political information related to countries or specific politicians, especially negative ones

    oai_token-act-pair · gemini-2.0-flash

    politics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     https
    -0.68
    https
    -0.60
    “
    -0.50
     “
    -0.49
    ’
    -0.48
     
    -0.45
    StringBuilder
    -0.43
    5
    -0.42
    4
    -0.41
    ,
    -0.41
    POSITIVE LOGITS
     kasarigan
    1.17
     Daß
    0.92
     Италијани
    0.90
    ^(@)
    0.89
    Demografia
    0.87
     مشين
    0.87
    SequentialGroup
    0.85
     /\.
    0.83
     Мексичка
    0.83
     mußte
    0.83
    Activations Density 14.450%

    No Known Activations