© 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. 106978
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    s
    1.16
    ।
    1.09
    ک
    1.07
    nd
    1.02
    st
    0.96
    r
    0.91
    ن
    0.89
    。
    0.88
    ।"
    0.87
    negara
    0.84
    POSITIVE LOGITS
    -
    1.00
    LE
    0.94
    ين
    0.88
    ING
    0.86
    هاي
    0.85
    The
    0.82
     niedr
    0.79
    ные
    0.78
     série
    0.78
     Usted
    0.78
    Activations Density 0.000%

    No Known Activations