© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115308
    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_27_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
     nitrous
    0.38
     mejorar
    0.38
     Surprisingly
    0.36
     Sco
    0.36
     dice
    0.35
     prostatic
    0.35
    矽
    0.35
     ASUS
    0.35
     shuffling
    0.34
     összef
    0.34
    POSITIVE LOGITS
    毕竟
    0.40
    annan
    0.39
    ileri
    0.39
     referring
    0.38
    endan
    0.38
    ıları
    0.37
     представ
    0.37
    λοι
    0.37
    豈
    0.37
    ภูมิ
    0.36
    Activations Density 0.000%

    No Known Activations