© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 254261
    Prev
    Next
    INDEX
    Explanations

    This

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    と思う
    0.40
    认为是
    0.38
    と思います
    0.36
    कार्य
    0.36
     grudge
    0.36
    لف
    0.36
    헬
    0.35
    と思いますが
    0.34
    िस्ट
    0.34
    Описание
    0.34
    POSITIVE LOGITS
     well
    0.51
     Completely
    0.50
     Starting
    0.48
     Well
    0.47
     To
    0.46
     잘
    0.46
     Release
    0.46
     Wellbeing
    0.44
     Wechsler
    0.43
    Well
    0.43
    Activations Density 0.004%

    No Known Activations