© 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. 9518
    Prev
    Next
    INDEX
    Explanations

    words related to political campaigns and donations

    oai_token-act-pair · gemini-2.0-flash

    fundraising related terms

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

    Donations

    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
    featureID
    -0.57
     Räume
    -0.54
    ropol
    -0.52
     fragility
    -0.51
    ühm
    -0.51
    NUMX
    -0.50
     endregion
    -0.50
     خبرگزاری
    -0.49
    ebaran
    -0.49
     Followed
    -0.48
    POSITIVE LOGITS
     sexuales
    0.73
    httphttps
    0.57
    enumi
    0.53
    köz
    0.50
    ünsche
    0.50
    PyTuple
    0.50
    IntoConstraints
    0.50
    
    0.49
    клопе
    0.48
    getSystemService
    0.48
    Activations Density 0.713%

    No Known Activations