© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 211189
    Prev
    Next
    INDEX
    Explanations

    zoom camera

    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_20_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
    ঝি
    0.38
    骚
    0.36
     приобрести
    0.35
     Veamos
    0.35
     Etiquetas
    0.34
     Joaqu
    0.34
    我又
    0.33
    ಮು
    0.32
    邛
    0.32
    옐
    0.32
    POSITIVE LOGITS
     historically
    0.39
     an
    0.36
     incrementally
    0.35
     statistically
    0.35
     শুনে
    0.35
     स्वराज
    0.35
     otomatis
    0.34
     waterfall
    0.34
     coherence
    0.34
     আট
    0.34
    Activations Density 0.002%

    No Known Activations