© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165113
    Prev
    Next
    INDEX
    Explanations

    fishing nets

    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_13_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
    ة
    0.54
     ON
    0.51
     Internationale
    0.49
     ঈদ
    0.49
     Yunnan
    0.48
     फ्रांस
    0.47
     Xinjiang
    0.45
     프랑
    0.45
    еры
    0.44
     सपनों
    0.44
    POSITIVE LOGITS
    酱
    0.42
     deseas
    0.41
    Amount
    0.40
    Street
    0.40
    Said
    0.40
    Partial
    0.40
     breasts
    0.39
     peaks
    0.38
    Approved
    0.38
    Detailed
    0.38
    Activations Density 0.002%

    No Known Activations