© 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. 168075
    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
     大型
    0.37
    ститу
    0.35
     పోటీ
    0.35
     конкур
    0.34
    紂
    0.34
    Parallel
    0.33
    Replacing
    0.33
     Replacing
    0.32
    aktur
    0.31
     ஒப்ப
    0.31
    POSITIVE LOGITS
     దశ
    0.37
     sigurn
    0.37
     Juan
    0.36
    VY
    0.36
    atience
    0.35
     نہیں۔
    0.35
    动
    0.35
     una
    0.34
    ัญหา
    0.34
     muchas
    0.34
    Activations Density 0.000%

    No Known Activations