© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202242
    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_12_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
    <0x0D>
    0.57
     erwartet
    0.54
     hva
    0.54
    ]
    0.52
    ชีพ
    0.52
     LON
    0.52
    "]
    0.51
    ಉ
    0.50
     inkjet
    0.49
     up
    0.49
    POSITIVE LOGITS
    рати
    0.57
    াণ
    0.54
    ají
    0.53
    ítě
    0.52
    汁
    0.52
    jati
    0.52
     पहाड़
    0.52
    apore
    0.49
    amish
    0.49
     Mountaine
    0.49
    Activations Density 0.000%

    No Known Activations