© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33384
    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
    Not in Any Lists

    No Comments

    Negative Logits
     duis
    0.43
    足够的
    0.42
    チェック
    0.38
     ordinate
    0.38
     тем
    0.38
    眝
    0.38
     aufgrund
    0.37
     suficient
    0.37
     screenplay
    0.37
     Sponsors
    0.37
    POSITIVE LOGITS
    уса
    0.44
    の値
    0.38
    ยา
    0.37
     짜
    0.37
    นาม
    0.37
     Vermeer
    0.36
     radi
    0.36
    xavier
    0.36
    voxel
    0.36
    helia
    0.36
    Activations Density 0.000%

    No Known Activations