© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 63570
    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_41_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
     idempotent
    0.39
    本格
    0.38
     retourner
    0.36
    撅
    0.34
     impos
    0.34
    تقل
    0.33
     wd
    0.33
    ﷲ
    0.33
     PRIN
    0.33
    bookmarks
    0.33
    POSITIVE LOGITS
     modified
    2.48
    modified
    2.38
    Modified
    2.34
     Modified
    2.27
     revised
    1.98
     amended
    1.93
     Revised
    1.80
     संशोधित
    1.75
     edited
    1.74
    Edited
    1.73
    Activations Density 0.000%

    No Known Activations