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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31816
    Prev
    Next
    INDEX
    Explanations

    statistical physics and complex systems

    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_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
     átomos
    0.40
     화학
    0.40
    invisible
    0.38
    transactions
    0.37
     immobile
    0.37
    អ
    0.36
     observables
    0.36
     Gross
    0.36
    INVISIBLE
    0.36
     συνα
    0.36
    POSITIVE LOGITS
    Backup
    0.42
    Backed
    0.40
    AAC
    0.39
     Backup
    0.38
    Private
    0.38
     Backbone
    0.38
     ♦
    0.38
    Male
    0.38
     lea
    0.36
     草
    0.36
    Activations Density 0.000%

    No Known Activations