© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 210856
    Prev
    Next
    INDEX
    Explanations

    loan disbursement or spending

    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_19_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
    несе
    0.46
     Lafayette
    0.43
    шек
    0.43
    rocław
    0.43
     (
    0.43
     бал
    0.42
    ке
    0.42
    ເຄື່ອງ
    0.42
    σω
    0.41
    ера
    0.41
    POSITIVE LOGITS
    Lane
    0.54
    Client
    0.47
    ட்ர
    0.46
    F
    0.45
     آد
    0.45
    Services
    0.45
     प्रिपरेशन
    0.44
    Share
    0.44
    Dependency
    0.44
    SearchResults
    0.43
    Activations Density 0.000%

    No Known Activations