© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 135491
    Prev
    Next
    INDEX
    Explanations

    equitable

    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_1_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
    กับ
    1.14
    Y
    1.05
    EY
    1.00
    </strong>
    1.00
    い
    0.97
    는
    0.95
    คุณ
    0.93
    どう
    0.91
    </h1>
    0.91
     कानून
    0.91
    POSITIVE LOGITS
    t
    1.68
     as
    1.38
     a
    1.22
    ig
    1.16
    க்கும்
    1.14
    y
    1.14
    től
    1.09
    ্য
    1.08
    ts
    1.05
     minimale
    1.05
    Activations Density 0.001%

    No Known Activations