© 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. 90936
    Prev
    Next
    INDEX
    Explanations

    conda environment

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ik
    0.59
    შ
    0.56
    ک
    0.55
     सारे
    0.54
     hicimos
    0.54
     αλλά
    0.52
     Barge
    0.52
    ก
    0.52
     सकेंगे
    0.51
    (""))
    0.51
    POSITIVE LOGITS
     in
    0.65
     don
    0.62
     Р
    0.58
     khoa
    0.57
    人
    0.55
    ोन
    0.53
     merchants
    0.53
     роботу
    0.52
     funded
    0.52
     femur
    0.52
    Activations Density 0.004%

    No Known Activations