© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 121659
    Prev
    Next
    INDEX
    Explanations

    stronger, higher, large, petites, more

    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_3_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
    you
    0.74
    ודי
    0.70
    ו
    0.68
    \}.
    0.66
    মন্ত্রীর
    0.64
    -]
    0.64
    赜
    0.63
    <unused0>
    0.62
     беше
    0.62
    ).'
    0.61
    POSITIVE LOGITS
    ية
    1.13
    е
    0.98
    w
    0.96
    il
    0.94
     is
    0.92
    ر
    0.91
    r
    0.88
    ’
    0.84
    ing
    0.82
    ре
    0.82
    Activations Density 0.000%

    No Known Activations