© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 206236
    Prev
    Next
    INDEX
    Explanations

    d, di, Dis, Dil, Dip, ใน

    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_37_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
     Được
    0.47
    棪
    0.43
     পূর্ববাংলার
    0.43
     পেতে
    0.41
     получите
    0.41
     कपकेक
    0.41
    lles
    0.39
    Ծ
    0.39
     অভিব্য
    0.39
    সন
    0.38
    POSITIVE LOGITS
     wants
    0.42
     mencoba
    0.42
     tries
    0.42
     tried
    0.40
     mener
    0.40
     reluctantly
    0.40
     ingin
    0.39
     consciously
    0.38
     /*
    0.38
    want
    0.38
    Activations Density 0.000%

    No Known Activations