© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156345
    Prev
    Next
    INDEX
    Explanations

    subordinating conjunction

    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_2_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
     on
    1.88
     to
    1.46
    л
    1.41
     at
    1.32
    ل
    1.30
    ל
    1.29
     όχι
    1.12
     onlar
    1.06
     onda
    1.05
     obey
    1.05
    POSITIVE LOGITS
    ка
    1.54
    <0x0D>
    1.45
    '
    1.18
    ك
    1.16
    (
    1.13
    де
    1.11
    ا
    1.11
    мимо
    1.05
    니다
    1.01
    этому
    1.01
    Activations Density 0.000%

    No Known Activations