© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58987
    Prev
    Next
    INDEX
    Explanations

    roundup, reel, suspects, mains, Staples, roster, hitters

    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
    s
    0.66
    กับ
    0.65
    o
    0.65
    ม
    0.59
    e
    0.56
    จาก
    0.55
    :")
    0.53
    จากการ
    0.51
    ")).
    0.51
    ]}$.
    0.49
    POSITIVE LOGITS
    ysteem
    0.57
     school
    0.57
    ponden
    0.56
    archivo
    0.55
    학교
    0.54
    的基本
    0.53
    conoc
    0.52
    culaire
    0.52
     articol
    0.52
     malades
    0.51
    Activations Density 0.029%

    No Known Activations