© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 36600
    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_50_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
     ਦਿ
    0.41
    ymb
    0.40
    Inn
    0.40
    邦
    0.39
    arium
    0.39
     symposium
    0.39
     جمه
    0.38
    olinium
    0.38
    玑
    0.38
    Reaction
    0.38
    POSITIVE LOGITS
     targets
    0.42
    μαν
    0.39
    targets
    0.38
     toca
    0.37
     truc
    0.36
    鮎
    0.35
     nen
    0.35
     pă
    0.34
     Сан
    0.34
     illeg
    0.34
    Activations Density 0.000%

    No Known Activations