© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 135124
    Prev
    Next
    INDEX
    Explanations

    special characters and common words

    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_1_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    2
    1.46
    一
    1.27
    로
    1.09
    Я
    1.05
    1
    1.04
    本
    1.03
    일
    1.03
    두
    0.98
     Remedies
    0.98
    Day
    0.98
    POSITIVE LOGITS
    า
    1.38
    ิ
    1.06
    ა
    1.01
     ре
    0.97
    al
    0.93
    m
    0.93
     a
    0.91
    ின்
    0.91
     sanguin
    0.89
     coucher
    0.89
    Activations Density 0.005%

    No Known Activations