© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 209612
    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_5_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
     to
    1.45
    ,
    1.35
    o
    1.30
    f
    1.30
    a
    1.24
     of
    1.22
    it
    1.17
     *
    1.16
    of
    1.14
    ai
    1.14
    POSITIVE LOGITS
    ви
    1.30
    هاي
    1.20
    ли
    1.17
     سي
    1.05
     مؤرشف
    1.00
    ал
    0.96
     يك
    0.95
    }$')
    0.95
    *}$
    0.95
    }$).
    0.94
    Activations Density 0.000%

    No Known Activations