© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84698
    Prev
    Next
    INDEX
    Explanations

    unaffiliated design, Jiefangbei (解放碑)

    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_0_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
    i
    2.06
    l
    1.51
    ي
    1.51
    iu
    1.38
    行う
    1.38
     for
    1.31
    ių
    1.31
    iin
    1.30
    含ま
    1.29
    ﻁ
    1.28
    POSITIVE LOGITS
    та
    2.00
    .
    1.88
    س
    1.70
    ьте
    1.60
    _
    1.59
    с
    1.55
    {
    1.55
    (
    1.41
    ıları
    1.38
    ти
    1.35
    Activations Density 0.000%

    No Known Activations