© 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
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 12110
    Prev
    Next
    INDEX
    Explanations

    Coast Guard

    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
     Stimme
    0.48
     Stairs
    0.48
     Coachella
    0.47
     Parties
    0.47
     Chili
    0.47
     Undang
    0.47
    <0xAA>
    0.46
     Partido
    0.46
     MTS
    0.45
     TSA
    0.45
    POSITIVE LOGITS
     डायरेक्टर
    0.49
    alen
    0.42
     شدن
    0.42
    強化
    0.41
     dibuka
    0.41
     boats
    0.40
    ванні
    0.39
     tempt
    0.38
     नहर
    0.38
    퍼
    0.38
    Activations Density 0.000%

    No Known Activations