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

    Neuronpedia

    Jacobian LensNEW
    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. 244956
    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
    নির্ম
    0.36
     حاج
    0.35
    ުޅ
    0.35
     نظر
    0.34
    🔋
    0.34
     emerg
    0.34
     मौसम
    0.34
    ẵn
    0.34
    িকভাবে
    0.33
    薨
    0.33
    POSITIVE LOGITS
     प्रदीप
    0.42
     dinn
    0.41
     Poh
    0.40
    appendText
    0.40
    accessdate
    0.38
     réseaux
    0.38
     Lomb
    0.38
     Prejudice
    0.38
     ulang
    0.37
     dynamo
    0.37
    Activations Density 0.000%

    No Known Activations