© 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. 143566
    Prev
    Next
    INDEX
    Explanations

    Next

    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
     Mariano
    0.39
     supplied
    0.38
     Micah
    0.38
     Marie
    0.38
     customizing
    0.37
    Profiles
    0.37
    桝
    0.37
     saving
    0.36
    "]}
    0.36
    が高
    0.36
    POSITIVE LOGITS
    pring
    0.46
    ंटी
    0.40
    avez
    0.40
     reinterpret
    0.39
    ystems
    0.37
     गोनी
    0.37
     vez
    0.36
     Hence
    0.36
    izedBox
    0.36
     civile
    0.36
    Activations Density 0.001%

    No Known Activations