© 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. 29630
    Prev
    Next
    INDEX
    Explanations

    learning objectives

    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
    úil
    0.39
     Magistrate
    0.37
    inventory
    0.35
    attutto
    0.35
     preparing
    0.34
     stir
    0.34
     gefragt
    0.34
     assassin
    0.34
    씰
    0.34
    primary
    0.33
    POSITIVE LOGITS
     learning
    1.62
    Learning
    1.62
     Learning
    1.59
    learning
    1.43
     LEAR
    1.35
    学习
    1.31
    學習
    1.31
    学習
    1.26
     लर्निंग
    1.23
     학습
    1.20
    Activations Density 0.005%

    No Known Activations