© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18691
    Prev
    Next
    INDEX
    Explanations

    health insurance, benefits, tax, residency, criminal record

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     eligibility
    0.48
    ⸱
    0.42
     Eligibility
    0.40
     کمک
    0.39
    埓
    0.39
     bantuan
    0.39
     arbitration
    0.39
    removed
    0.38
    violin
    0.38
     खाद
    0.37
    POSITIVE LOGITS
     trận
    0.40
    Disposition
    0.39
     누
    0.38
     అల
    0.37
    еве
    0.37
     TIC
    0.37
     Positions
    0.36
    emt
    0.36
     Balashov
    0.36
    AssetName
    0.36
    Activations Density 0.025%

    No Known Activations