© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 232935
    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_6_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
    يد
    1.20
    <unused2140>
    1.03
    اني
    1.01
    يت
    1.00
    <0x0D>
    1.00
    كي
    0.99
    يل
    0.98
    كو
    0.97
    ט
    0.96
    شي
    0.94
    POSITIVE LOGITS
    IN
    1.15
    -
    0.98
    el
    0.95
     incontinence
    0.95
    ares
    0.93
    ed
    0.92
    aito
    0.92
    aa
    0.91
    In
    0.89
    ↵
    0.88
    Activations Density 0.000%

    No Known Activations