© 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. 2109
    Prev
    Next
    INDEX
    Explanations

    second tranche

    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
    ⎙
    0.39
    orealistic
    0.38
     Boys
    0.37
     প্রদান
    0.36
    sol
    0.36
    是一種
    0.36
    त्र
    0.35
    obic
    0.35
    DEP
    0.35
     @"
    0.34
    POSITIVE LOGITS
     insertion
    0.46
     Insertion
    0.39
     insertions
    0.39
    insertion
    0.38
     volume
    0.37
    Insertion
    0.36
     inserting
    0.36
     Jumbo
    0.36
     lung
    0.35
     activated
    0.35
    Activations Density 0.130%

    No Known Activations