© 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. 218397
    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
     ఉద్య
    0.39
     voorkomen
    0.38
     असलेला
    0.38
     العن
    0.36
    ျေး
    0.36
    坭
    0.36
     الآن
    0.36
     capitalise
    0.36
     स्क्वायर
    0.35
    Artikel
    0.35
    POSITIVE LOGITS
    霆
    0.38
     Caribbean
    0.37
     proper
    0.36
    est
    0.35
    pitch
    0.35
    čkog
    0.35
    heart
    0.34
     cellular
    0.34
     सिन्हा
    0.34
     burning
    0.34
    Activations Density 0.000%

    No Known Activations