© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 226830
    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_10_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
    ные
    0.58
    ה
    0.54
    农
    0.53
    па
    0.52
    поло
    0.51
    ो
    0.51
    ట్
    0.48
    ة
    0.48
    пол
    0.48
    amazaki
    0.48
    POSITIVE LOGITS
    vdd
    0.48
    😏
    0.48
    ServiceObject
    0.47
     veng
    0.44
     😏
    0.44
    business
    0.44
     vultures
    0.43
    😉
    0.43
     Debt
    0.42
    NeedConnect
    0.42
    Activations Density 0.000%

    No Known Activations