© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 221314
    Prev
    Next
    INDEX
    Explanations

    allows the

    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_31_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
    imper
    0.40
    icans
    0.39
    人は
    0.39
    බ
    0.39
    ване
    0.39
    人が
    0.37
     sensors
    0.37
    老大
    0.37
     Ary
    0.37
    Dü
    0.36
    POSITIVE LOGITS
     inoculation
    0.41
    azor
    0.38
    VRDR
    0.37
     dito
    0.36
     boxShadow
    0.36
     stare
    0.36
     "=
    0.35
    gares
    0.35
     জানিয়েছিলেন
    0.35
     staring
    0.34
    Activations Density 0.006%

    No Known Activations