© 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. 106878
    Prev
    Next
    INDEX
    Explanations

    ganar

    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
    ק
    1.30
    ک
    1.15
    ب
    1.05
    し
    1.05
    ה
    0.98
    t
    0.90
    א
    0.90
    ुल्लाह
    0.84
    il
    0.83
    ۰
    0.82
    POSITIVE LOGITS
     in
    1.59
    在
    1.39
    in
    1.12
    SE
    1.10
    在国内
    1.07
    notin
    1.05
    在那里
    1.02
     \$
    1.00
     indien
    0.99
    U
    0.98
    Activations Density 0.000%

    No Known Activations