© 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-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23121
    Prev
    Next
    INDEX
    Explanations

    political campaign donations

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bil
    1.29
     Bil
    1.17
    Bil
    1.15
     빌
    1.05
     Bill
    0.98
    bil
    0.95
     BIL
    0.88
    빌
    0.86
     ke
    0.84
     bili
    0.80
    POSITIVE LOGITS
     campaign
    0.61
     Campaign
    0.57
    Campaign
    0.57
    campaign
    0.54
     invoices
    0.52
     invoice
    0.51
    invoice
    0.49
     campanha
    0.47
    Invoice
    0.43
    吹
    0.43
    Activations Density 0.004%

    No Known Activations