© 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. 90196
    Prev
    Next
    INDEX
    Explanations

    (m/w/d)

    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
    ᖇ
    0.40
     тяж
    0.38
     T
    0.38
     MOR
    0.38
     dece
    0.37
     Thrones
    0.36
     dust
    0.35
     পড়েন
    0.35
    న్స్‌
    0.35
     ~
    0.35
    POSITIVE LOGITS
    কিন্তু
    0.46
    当初
    0.42
     كيفية
    0.39
    <0x81>
    0.39
     qualsiasi
    0.39
     mainWindow
    0.39
    isRequired
    0.38
     نحو
    0.38
    მოს
    0.38
    แต่
    0.38
    Activations Density 0.001%

    No Known Activations