© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164391
    Prev
    Next
    INDEX
    Explanations

    plants and growth (bear, inherit, planted, anywhere)

    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_31_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
    
    0.40
     hack
    0.39
    cmds
    0.37
     workaround
    0.37
     subcommand
    0.34
     erweitert
    0.34
     நடந்த
    0.34
     forcible
    0.34
    擔心
    0.34
     commanded
    0.34
    POSITIVE LOGITS
    穂
    0.43
    Kas
    0.40
     Kas
    0.39
     motorised
    0.39
     Casi
    0.39
    Stem
    0.39
     hydroelectric
    0.38
    莴
    0.38
     underwater
    0.38
     cassette
    0.38
    Activations Density 0.001%

    No Known Activations