© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27942
    Prev
    Next
    INDEX
    Explanations

    opera and ballet companies

    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
    मोर
    0.37
    މ
    0.37
    če
    0.37
    uncio
    0.37
    żyt
    0.36
    镑
    0.36
    鱈
    0.36
    มอ
    0.36
    African
    0.36
     higiene
    0.36
    POSITIVE LOGITS
     company
    0.59
     कंपनी
    0.59
    company
    0.59
     compañía
    0.59
     કંપની
    0.59
     compagnie
    0.58
     compagnia
    0.56
     компания
    0.54
    companies
    0.54
     companhia
    0.54
    Activations Density 0.016%

    No Known Activations