© 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. 30235
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and definitions

    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
     Mikh
    0.39
    nomina
    0.38
    িলম্বে
    0.36
     खुल
    0.35
     converged
    0.35
    InitStructure
    0.34
    <0xF2>
    0.34
     quod
    0.34
     whereby
    0.33
    ardust
    0.33
    POSITIVE LOGITS
    資金
    0.36
    برى
    0.33
     všetky
    0.32
     derajat
    0.31
     ：
    0.31
     दर
    0.30
    ForItem
    0.30
     ایپ
    0.30
    žia
    0.30
     croc
    0.30
    Activations Density 0.090%

    No Known Activations