© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 154538
    Prev
    Next
    INDEX
    Explanations

    batch operations or bulk processing

    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_23_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
    烔
    0.41
     потрі
    0.40
    愆
    0.39
    分离
    0.38
    dichloro
    0.37
    棸
    0.36
    笤
    0.36
     isolé
    0.36
    陴
    0.36
     دیگر
    0.35
    POSITIVE LOGITS
     marathon
    0.46
     Merlin
    0.44
    omena
    0.43
     max
    0.41
     Meets
    0.40
    राबाद
    0.39
     Marathon
    0.39
     bấm
    0.39
    器
    0.39
     brave
    0.38
    Activations Density 0.002%

    No Known Activations