© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208940
    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_20_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
    recursive
    0.44
    brush
    0.43
    蒼
    0.42
    .?
    0.42
     निवेश
    0.41
    line
    0.40
    Mk
    0.39
    .*
    0.39
    geometric
    0.39
     जिन्होंने
    0.38
    POSITIVE LOGITS
     consomm
    0.46
     sıra
    0.46
     Cuisine
    0.45
    琤
    0.45
    祹
    0.42
     naam
    0.42
     Flughafen
    0.41
     ενεργ
    0.41
     کھانا
    0.41
     минут
    0.41
    Activations Density 0.000%

    No Known Activations