© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89027
    Prev
    Next
    INDEX
    Explanations

    workforce, Fitzgerald, housemaid, solar system

    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_3_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
    した
    0.91
    할
    0.84
    ствия
    0.77
    ية
    0.74
    い
    0.72
    elijke
    0.71
    ين
    0.70
    ία
    0.69
    ט
    0.68
    ى
    0.67
    POSITIVE LOGITS
    (
    0.64
    น
    0.60
    ↵
    0.60
    9
    0.59
     Regulator
    0.57
    3
    0.57
               
    0.56
    -
    0.56
     regulators
    0.55
    กับการ
    0.55
    Activations Density 0.006%

    No Known Activations