© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 93269
    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_11_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
    ۰
    0.54
     wartości
    0.53
     நன்றாக
    0.52
    Lk
    0.52
     கரி
    0.50
     کر
    0.50
     성능
    0.50
     университета
    0.50
     curso
    0.49
     pleasure
    0.48
    POSITIVE LOGITS
    冠
    0.46
    sock
    0.44
    量子
    0.44
    closes
    0.43
    italization
    0.43
    名
    0.43
    移植
    0.42
    里
    0.41
    PSP
    0.41
    古代
    0.41
    Activations Density 0.000%

    No Known Activations