© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 206652
    Prev
    Next
    INDEX
    Explanations

    say "tract"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     excav
    0.45
    洄
    0.39
     debugger
    0.38
     Stav
    0.38
    Stub
    0.37
     Rave
    0.37
    बैक
    0.37
    烔
    0.36
     stub
    0.36
    رداری
    0.36
    POSITIVE LOGITS
     tract
    2.20
     Tract
    2.19
     трак
    2.11
    tract
    2.00
     trakt
    2.00
     tractor
    1.91
     tracts
    1.86
     Tractor
    1.76
    tractor
    1.74
     tractors
    1.69
    Activations Density 0.001%

    No Known Activations