© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 51901
    Prev
    Next
    INDEX
    Explanations

    guilty pleasure; guilty gear

    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_10_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
    st
    0.28
    。
    0.26
    inin
    0.24
    ড
    0.24
    ।"
    0.23
    6
    0.23
    in
    0.23
    ।
    0.22
    F
    0.22
    ut
    0.22
    POSITIVE LOGITS
    ல்
    0.30
    ли
    0.29
    вание
    0.27
    вина
    0.25
    ів
    0.25
    نا
    0.25
     gmin
    0.24
    会出现
    0.24
    quakes
    0.24
    లు
    0.24
    Activations Density 0.010%

    No Known Activations