© 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. 167918
    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
    以外の
    0.44
     例文帳に追加
    0.41
     مهما
    0.40
    ją
    0.40
     желе
    0.40
     FIXED
    0.39
    𝙍
    0.39
    ANDROID
    0.38
     Whatever
    0.38
     Hopefully
    0.38
    POSITIVE LOGITS
     bonheur
    0.41
     telef
    0.40
    嗲
    0.39
     tn
    0.39
     flock
    0.36
     variante
    0.36
     halt
    0.36
    曠
    0.36
     boda
    0.36
    ങ്ങളാണ്
    0.36
    Activations Density 0.000%

    No Known Activations