© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4198
    Prev
    Next
    INDEX
    Explanations

    symbolic formation

    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_40_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
     હત
    0.33
     اجتماع
    0.30
    IDS
    0.29
    ifle
    0.29
     emoz
    0.29
     ક્લિક
    0.29
    ழந்த
    0.29
    Recognition
    0.28
    oci
    0.28
    桢
    0.28
    POSITIVE LOGITS
     formed
    0.55
     형성
    0.50
     formé
    0.43
     formée
    0.43
     formado
    0.43
     forming
    0.40
     сформи
    0.40
    形成
    0.39
    SYMBOL
    0.39
     образу
    0.39
    Activations Density 0.079%

    No Known Activations