© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 83235
    Prev
    Next
    INDEX
    Explanations

    F

    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_53_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
    東
    0.39
     Ear
    0.38
    现代
    0.38
     Publication
    0.37
    τας
    0.36
     Michal
    0.36
    东
    0.36
     Earnings
    0.36
    𝗷
    0.36
     Mix
    0.35
    POSITIVE LOGITS
     aggressiveness
    0.46
     alt
    0.38
    Importer
    0.38
     canton
    0.38
    cience
    0.38
    below
    0.37
    মত
    0.36
    GAMMA
    0.36
    िल
    0.36
     agron
    0.36
    Activations Density 0.007%

    No Known Activations