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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 164890
    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_13_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
    सेस
    0.49
    醀
    0.48
    जैसा
    0.45
     vasodilator
    0.45
    只要
    0.44
     Seperti
    0.44
    ण्यासाठी
    0.44
    д
    0.44
     berhasil
    0.44
    靠近
    0.43
    POSITIVE LOGITS
    y
    0.67
    ON
    0.58
    es
    0.56
    }"
    0.56
    rew
    0.55
    os
    0.54
    ()
    0.54
    s
    0.53
    aplan
    0.52
     gentleman
    0.52
    Activations Density 0.000%

    No Known Activations