© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16377
    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_40_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
     Naked
    0.40
    裸
    0.39
     बिक
    0.39
    reduced
    0.39
    profil
    0.38
    Klein
    0.38
     Pf
    0.38
     naked
    0.37
    naked
    0.36
    綬
    0.36
    POSITIVE LOGITS
    ┤
    0.44
     परवरिश
    0.43
    prayer
    0.43
     молит
    0.42
     Prayer
    0.42
     prayer
    0.42
    ปลอดภัย
    0.41
     secretNumber
    0.41
    祷
    0.41
     wax
    0.40
    Activations Density 0.013%

    No Known Activations