© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 212153
    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_20_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
    ப்புகள்
    0.18
     Amin
    0.18
    বর্ষ
    0.18
     наиболь
    0.17
     Oliver
    0.16
    เทศ
    0.16
     ዓ
    0.16
    ต่ำ
    0.16
     Laurence
    0.16
     Aufgrund
    0.16
    POSITIVE LOGITS
    haman
    0.21
    шенко
    0.20
    america
    0.19
    Mania
    0.19
     stessa
    0.19
     spagn
    0.19
     vaga
    0.19
    spannung
    0.19
    <unused2115>
    0.19
     permangan
    0.18
    Activations Density 0.000%

    No Known Activations