© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 9986
    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_40_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
     vent
    0.38
     Gui
    0.38
    vent
    0.37
    木
    0.37
     সাইফুদ্দিন
    0.37
     மர
    0.37
     Conform
    0.36
    yship
    0.36
     Lí
    0.36
     Forward
    0.35
    POSITIVE LOGITS
     hermit
    0.40
     crab
    0.40
    '])){
    0.39
     زائ
    0.39
     salinity
    0.38
     Crab
    0.38
     слай
    0.38
    izmu
    0.37
     Cr
    0.37
    ())){
    0.36
    Activations Density 0.028%

    No Known Activations