© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 168145
    Prev
    Next
    INDEX
    Explanations

    common items

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    不
    1.72
     不
    1.18
     불
    1.16
    불
    0.96
    ไม่
    0.86
    不
    0.80
    的不
    0.78
     tidak
    0.75
    nicht
    0.75
     не
    0.74
    POSITIVE LOGITS
    床
    0.48
    牀
    0.44
     bed
    0.42
    弃
    0.39
     Bed
    0.39
     anvil
    0.38
     bug
    0.37
    是大
    0.37
    üsü
    0.36
     Habib
    0.36
    Activations Density 0.002%

    No Known Activations