© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46493
    Prev
    Next
    INDEX
    Explanations

    mortgage payments processing

    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_3_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
     amoureux
    0.68
     edilen
    0.68
    見える
    0.67
     auricular
    0.67
     بنائے
    0.67
     α
    0.66
     یا
    0.66
     в
    0.66
     antibacterial
    0.65
     сообщи
    0.64
    POSITIVE LOGITS
    م
    0.72
    ER
    0.71
    ه
    0.68
    ان
    0.67
    تك
    0.67
    et
    0.65
    ين
    0.65
    ar
    0.64
    شك
    0.61
    ث
    0.61
    Activations Density 0.001%

    No Known Activations