© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215928
    Prev
    Next
    INDEX
    Explanations

    framework

    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_5_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
     in
    1.55
    \
    1.45
    '
    1.21
    ज
    1.15
     inaccur
    1.09
     fluctu
    1.06
     fluctuations
    1.06
    )
    1.06
     incarcer
    1.05
    -
    1.05
    POSITIVE LOGITS
    مان
    1.45
    u
    1.42
    you
    1.23
    1
    1.22
    nex
    1.19
    ו
    1.17
    nél
    1.15
    nings
    1.13
    нено
    1.09
    do
    1.04
    Activations Density 0.005%

    No Known Activations