© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257184
    Prev
    Next
    INDEX
    Explanations

    square root

    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_22_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
    Dod
    0.39
     Dodger
    0.39
     memorandum
    0.39
    ENDMENT
    0.37
    ழிய
    0.37
     Memorandum
    0.35
    Worker
    0.35
     striker
    0.34
     digamos
    0.34
    煤
    0.34
    POSITIVE LOGITS
     léč
    0.39
     Brussels
    0.37
    etimes
    0.37
    edly
    0.35
     cheeky
    0.35
     Canberra
    0.35
    cemic
    0.35
    mib
    0.35
    ivity
    0.34
     القاهرة
    0.34
    Activations Density 0.001%

    No Known Activations