© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28238
    Prev
    Next
    INDEX
    Explanations

    parade or procession

    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
    y
    0.84
    1
    0.69
    ia
    0.67
    :
    0.61
     .
    0.61
    uk
    0.61
    ian
    0.60
    ONG
    0.59
    า
    0.58
    ma
    0.58
    POSITIVE LOGITS
     parade
    0.63
     Сен
    0.57
     Зна
    0.55
    지
    0.52
    ίου
    0.49
     vattati
    0.49
    ин
    0.49
    ístico
    0.48
    이드
    0.48
    ες
    0.46
    Activations Density 0.012%

    No Known Activations