© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232273
    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_32_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
    ğimiz
    0.38
     يكون
    0.37
     nghị
    0.36
    （
    0.35
    ́i
    0.35
    Base
    0.34
    Note
    0.34
    Salta
    0.34
     Base
    0.34
    Conditional
    0.34
    POSITIVE LOGITS
    脱
    0.44
    生活中
    0.40
    탈
    0.40
    脫
    0.39
     bodily
    0.39
    今まで
    0.38
     zuletzt
    0.37
     działalności
    0.37
    これまで
    0.37
     കേസ
    0.36
    Activations Density 0.000%

    No Known Activations