© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215022
    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_31_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
     theoret
    0.41
    ಊ
    0.40
    theoretic
    0.40
    practical
    0.39
    anthus
    0.38
    फर
    0.38
     grosses
    0.37
    Practical
    0.36
     praktische
    0.36
    炲
    0.36
    POSITIVE LOGITS
    த்திற்க
    0.44
    涮
    0.40
     Azz
    0.39
     MIND
    0.38
    六
    0.38
     Gilman
    0.37
     EC
    0.37
    医師
    0.37
     kmeans
    0.37
     Macdonald
    0.37
    Activations Density 0.000%

    No Known Activations