© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 207636
    Prev
    Next
    INDEX
    Explanations

    say ":"

    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
    Negative Logits
     eich
    0.38
    reste
    0.38
    孵
    0.37
    řed
    0.36
    Override
    0.35
    Deps
    0.35
     დაკ
    0.34
    nullable
    0.34
    Fet
    0.34
    แดง
    0.34
    POSITIVE LOGITS
    })(\
    0.40
     stages
    0.38
     giai
    0.38
     choosing
    0.38
     consolidating
    0.38
     blames
    0.38
     আসেনি
    0.38
     til
    0.37
     ກ
    0.37
     Gui
    0.37
    Activations Density 0.005%

    No Known Activations