© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28877
    Prev
    Next
    INDEX
    Explanations

    mortgage-backed securities

    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_10_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
     que
    0.60
    é
    0.57
     politico
    0.55
     país
    0.54
     πάντα
    0.54
    ó
    0.54
    ி
    0.54
    ſe
    0.52
     fruitless
    0.51
     cadáver
    0.51
    POSITIVE LOGITS
    Sign
    0.57
     Mortgage
    0.57
    Tanggal
    0.55
    Й
    0.55
    Book
    0.54
    жат
    0.54
    Diagram
    0.52
    Թ
    0.52
     Immobilien
    0.51
    Survey
    0.51
    Activations Density 0.016%

    No Known Activations