© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    4. 88710
    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_18_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
    ضل
    0.51
    :
    0.50
     :
    0.48
     Fie
    0.48
    悰
    0.47
     Сти
    0.46
    :_
    0.46
    blueberry
    0.45
    akyat
    0.44
    Задача
    0.44
    POSITIVE LOGITS
     型
    0.46
     widely
    0.44
     mniej
    0.44
    woff
    0.43
     arresting
    0.43
     値
    0.43
    vić
    0.43
    sometimes
    0.42
    ួត
    0.42
    Nom
    0.42
    Activations Density 0.000%

    No Known Activations