© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164420
    Prev
    Next
    INDEX
    Explanations

    Inca royalty, Mason, prayer style

    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_31_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
     chicks
    0.42
     drums
    0.39
    綿
    0.39
    彬
    0.39
    ন্ন
    0.38
     penn
    0.37
    dependencies
    0.36
     evanescent
    0.36
    unct
    0.36
     becoming
    0.36
    POSITIVE LOGITS
    Neutral
    0.44
    讧
    0.40
     Neutral
    0.38
    Atlas
    0.37
     Takashi
    0.37
    Sau
    0.36
     சமா
    0.36
    啓
    0.36
    ಿದ್ದರು
    0.34
    үз
    0.34
    Activations Density 0.000%

    No Known Activations