© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 92079
    Prev
    Next
    INDEX
    Explanations

    describing states or items

    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_11_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
    的我
    0.51
     한
    0.49
     Leider
    0.46
     함
    0.46
    宄
    0.46
     leider
    0.44
     చి
    0.43
     bạn
    0.42
    한
    0.42
     치
    0.42
    POSITIVE LOGITS
     dominates
    0.56
     amass
    0.49
     earphones
    0.49
     wallpaper
    0.48
    asz
    0.47
     sediments
    0.47
     defenders
    0.46
     animali
    0.46
     frescos
    0.46
    ogliere
    0.46
    Activations Density 0.000%

    No Known Activations