© 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. 161219
    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
    െന്നാണ്
    0.37
    ებზე
    0.37
     desempe
    0.37
     แก้
    0.36
    ல்களை
    0.35
    դ
    0.35
    ზე
    0.35
    හු
    0.34
    ependant
    0.34
    datab
    0.34
    POSITIVE LOGITS
     abst
    0.39
     abstain
    0.38
    ogia
    0.36
    딩
    0.36
     tolerant
    0.36
     overrun
    0.36
     dãy
    0.35
     проверя
    0.35
    ّم
    0.34
     Reinh
    0.34
    Activations Density 0.000%

    No Known Activations