© 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. 30382
    Prev
    Next
    INDEX
    Explanations

    past continuous verbs

    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
     хоть
    0.23
     fuga
    0.23
     seda
    0.22
     archiv
    0.22
    虽然
    0.21
    kova
    0.21
    ंगाना
    0.21
     состоя
    0.21
    속
    0.21
     RECEIVED
    0.21
    POSITIVE LOGITS
     thisTrack
    0.27
    frameNStart
    0.26
    aces
    0.24
    堺
    0.24
    javaHome
    0.23
    allax
    0.23
     EditorGUILayout
    0.23
     Atom
    0.23
    "=>
    0.22
     Null
    0.22
    Activations Density 0.000%

    No Known Activations