© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92248
    Prev
    Next
    INDEX
    Explanations

    trouble or burden

    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_11_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
     vocal
    0.52
     działania
    0.52
     tokenize
    0.52
    duire
    0.52
     tokenizer
    0.51
    žil
    0.50
    囵
    0.50
     hydroxyl
    0.50
    žu
    0.50
     grayish
    0.49
    POSITIVE LOGITS
    у
    0.64
     Meeting
    0.63
    A
    0.62
    чных
    0.61
    q
    0.59
     W
    0.59
     A
    0.58
    sion
    0.58
     asked
    0.57
     Yes
    0.57
    Activations Density 0.000%

    No Known Activations