© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14878
    Prev
    Next
    INDEX
    Explanations

    cabaret and Parisian nightlife

    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
    kub
    0.36
    liegen
    0.34
    स्तु
    0.34
     Ingeniería
    0.33
    簷
    0.33
    ken
    0.33
     дроб
    0.33
    ^{(
    0.33
    elton
    0.33
    檐
    0.33
    POSITIVE LOGITS
     cabaret
    0.82
     cab
    0.66
     Parisian
    0.66
     Moulin
    0.60
    Cab
    0.60
     Paris
    0.59
     Cab
    0.59
     CAB
    0.57
    cab
    0.56
     chanson
    0.55
    Activations Density 0.033%

    No Known Activations