© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 122596
    Prev
    Next
    INDEX
    Explanations

    red error messages

    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_38_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
     ----------
    0.41
    流
    0.41
    Descriptors
    0.39
    流
    0.38
     CHAPTER
    0.38
     peas
    0.38
    Chapter
    0.38
    chapter
    0.37
    BASIC
    0.37
    ❐
    0.37
    POSITIVE LOGITS
    positroid
    0.45
    correcto
    0.39
    เร็จ
    0.38
     укра
    0.37
     dekor
    0.37
     funcionalidades
    0.37
     kara
    0.37
     %>',
    0.37
     पड़ता
    0.36
    DeathRecord
    0.36
    Activations Density 0.000%

    No Known Activations