© 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. 33658
    Prev
    Next
    INDEX
    Explanations

    sea level, mountain, volcano

    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
    ளாக
    0.37
    灏
    0.35
     PAV
    0.35
     regaining
    0.34
     quadratic
    0.34
     Quadratic
    0.34
     efficiency
    0.33
    ーブ
    0.33
     वृद्धा
    0.33
    icator
    0.33
    POSITIVE LOGITS
     Staples
    0.39
    fragment
    0.37
     விளக்கம்
    0.36
     abhiv
    0.35
    눕
    0.35
     Wain
    0.34
     jan
    0.34
     फुल
    0.34
    anthem
    0.34
     mexico
    0.34
    Activations Density 0.012%

    No Known Activations