© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 59059
    Prev
    Next
    INDEX
    Explanations

    calloused finger

    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
     forbade
    0.65
     процесса
    0.59
     appareils
    0.59
     extol
    0.59
     chuckled
    0.58
    স
    0.58
    ม
    0.58
     bunches
    0.57
     unsh
    0.57
     navigateur
    0.56
    POSITIVE LOGITS
     Rebellion
    0.56
    o
    0.53
     Festival
    0.53
    ؤال
    0.51
     Investment
    0.50
    3
    0.50
     Keating
    0.50
    KOM
    0.50
     Rehabilitation
    0.50
    FileSystem
    0.49
    Activations Density 0.000%

    No Known Activations