© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 205465
    Prev
    Next
    INDEX
    Explanations

    extracting structured data

    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_20_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
    德
    0.37
     aru
    0.34
    cił
    0.34
     Beyer
    0.33
    ♤
    0.33
    କ୍
    0.32
    nds
    0.32
    ंडे
    0.31
    spj
    0.31
     Outdoors
    0.31
    POSITIVE LOGITS
     inflammatory
    0.42
     VOC
    0.39
     curative
    0.38
    borderwidth
    0.38
     injured
    0.37
     عدد
    0.37
     indicative
    0.36
     inclusive
    0.36
     surgical
    0.36
     Ừ
    0.35
    Activations Density 0.016%

    No Known Activations