© 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. 33499
    Prev
    Next
    INDEX
    Explanations

    programming operations like get and commit

    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
    Manufact
    0.17
     bun
    0.16
    �
    0.16
    bun
    0.16
    がい
    0.16
     vật
    0.15
    人
    0.15
    High
    0.15
    ‘
    0.15
     connected
    0.15
    POSITIVE LOGITS
    ㅃ
    0.17
    ্থিত
    0.17
     एंड्र
    0.17
     ethernet
    0.17
    ENCIAS
    0.17
     നെറ്റ്‌വർ
    0.16
     জয়ের
    0.16
     হলিউ
    0.16
    ንያ
    0.16
    রাজের
    0.16
    Activations Density 0.001%

    No Known Activations