© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4311
    Prev
    Next
    INDEX
    Explanations

    nonlinear optical phenomena

    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_40_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
    צא
    0.40
    multiSelectList
    0.40
     lingue
    0.39
     Sprach
    0.38
     निकाल
    0.38
     електри
    0.38
    飆
    0.37
     Motiv
    0.37
    ⿻
    0.37
     motivates
    0.37
    POSITIVE LOGITS
    sten
    0.38
    ston
    0.37
    ateria
    0.35
    endes
    0.35
     पाय
    0.35
    উত্তরঃ
    0.35
     Phila
    0.34
    hausen
    0.34
     EXPRESS
    0.34
    攪
    0.34
    Activations Density 0.001%

    No Known Activations