© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257308
    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_22_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
    τι
    0.45
    ΙΑ
    0.44
     JAMES
    0.43
    ﺪ
    0.42
    καν
    0.42
    ﭥ
    0.41
    Curtis
    0.41
     Dene
    0.41
     அக்க
    0.40
     سٹ
    0.40
    POSITIVE LOGITS
     부
    0.45
     confronts
    0.44
    GPU
    0.44
     idols
    0.44
    ளம்
    0.43
    rawler
    0.43
     слу
    0.42
    puff
    0.41
    aing
    0.41
     demonstrate
    0.41
    Activations Density 0.000%

    No Known Activations