© 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. 161306
    Prev
    Next
    INDEX
    Explanations

    "what is" questions and defining terms

    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
     obtus
    0.37
    нутри
    0.34
    Brend
    0.33
    Nexus
    0.33
    atius
    0.33
    颔
    0.33
     recinto
    0.32
    ोजा
    0.32
    UGH
    0.32
     канце
    0.32
    POSITIVE LOGITS
     estate
    0.38
     planning
    0.38
     Estate
    0.36
    planning
    0.35
    ඵ
    0.34
     birefringence
    0.32
    Ņ
    0.32
     Jeux
    0.32
     housework
    0.32
    IamPolicy
    0.31
    Activations Density 0.012%

    No Known Activations