© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19818
    Prev
    Next
    INDEX
    Explanations

    identifying what was written

    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_15_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
     হবে
    0.58
     νέα
    0.55
    aremos
    0.54
     nuevos
    0.54
     nieuwe
    0.54
     nuevas
    0.52
     যাবেন
    0.52
    ḵ
    0.52
     neue
    0.51
    bewerken
    0.51
    POSITIVE LOGITS
     formed
    0.55
     sometimes
    0.48
     oil
    0.48
     faces
    0.47
    न्ति
    0.47
    ﻲ
    0.47
     menace
    0.46
    •
    0.45
    צ
    0.45
     油
    0.45
    Activations Density 0.000%

    No Known Activations