© 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. 7070
    Prev
    Next
    INDEX
    Explanations

    instances of political and social issues being discussed

    oai_token-act-pair · gemini-2.0-flash

    controversial social issues

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

    political issues

    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
     vícti
    -0.52
     tengah
    -0.50
     diametro
    -0.46
    fører
    -0.45
     hvě
    -0.45
    gesch
    -0.44
    Clik
    -0.44
     découver
    -0.43
     generación
    -0.43
     utford
    -0.43
    POSITIVE LOGITS
     abortion
    0.80
    Autoritní
    0.79
    ListItemIcon
    0.78
     homosexuality
    0.72
     Brexit
    0.71
     climate
    0.71
    DockStyle
    0.70
     Obamacare
    0.69
    featureID
    0.69
     divorce
    0.69
    Activations Density 6.278%

    No Known Activations