© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 29987
    Prev
    Next
    INDEX
    Explanations

    checkup

    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_7_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
    ን
    0.86
    터
    0.84
    촉
    0.84
    ﻄ
    0.82
    كر
    0.81
    자의
    0.80
    의
    0.80
    리
    0.79
    ﺮ
    0.77
    ках
    0.75
    POSITIVE LOGITS
    t
    1.17
    em
    1.11
    il
    0.98
    ↵
    0.95
     I
    0.91
    ,
    0.91
    to
    0.85
    ti
    0.83
    l
    0.82
    ie
    0.81
    Activations Density 0.000%

    No Known Activations