© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 140236
    Prev
    Next
    INDEX
    Explanations

    both, two, traditional

    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_37_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
    ژن
    0.40
    টির
    0.39
     তথা
    0.38
     encuentros
    0.38
     యొక్క
    0.37
    streams
    0.37
    щений
    0.37
    ]]))
    0.37
    ্ক
    0.36
     itself
    0.35
    POSITIVE LOGITS
    两者
    0.43
    传统的
    0.42
     两
    0.41
     दोघा
    0.40
     બંને
    0.40
    Two
    0.39
     Two
    0.39
     Part
    0.39
    தையும்
    0.39
    Traditional
    0.38
    Activations Density 0.011%

    No Known Activations