© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 223323
    Prev
    Next
    INDEX
    Explanations

    fixated

    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_10_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
     (
    0.76
     pest
    0.75
     true
    0.72
     time
    0.72
     stud
    0.71
     flores
    0.70
     faculty
    0.68
     duty
    0.67
    er
    0.67
     process
    0.67
    POSITIVE LOGITS
    س
    1.02
    ों
    0.97
    স
    0.90
    ０
    0.89
    ০
    0.85
    ک
    0.82
    स
    0.81
    ພວກເຮົາ
    0.79
    ক
    0.79
    0
    0.77
    Activations Density 0.000%

    No Known Activations