© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40003
    Prev
    Next
    INDEX
    Explanations

    discounting price reduction

    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_11_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
     THEY
    0.63
     gewann
    0.62
     conclude
    0.61
     COULD
    0.59
     =
    0.56
     wurde
    0.56
     leveraging
    0.56
     WILL
    0.55
     standoff
    0.55
     burglary
    0.55
    POSITIVE LOGITS
    aws
    0.65
    asts
    0.59
    taining
    0.57
    readers
    0.57
    考虑到
    0.55
    imo
    0.54
     عالمی
    0.54
    t
    0.54
    Considering
    0.53
    ב
    0.52
    Activations Density 0.001%

    No Known Activations