© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 157915
    Prev
    Next
    INDEX
    Explanations

    buildings and towers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     NIG
    0.39
    脱毛
    0.39
     Nakamura
    0.38
    恽
    0.37
    volta
    0.37
     demokrasi
    0.36
    انا
    0.36
     судо
    0.36
     anatomy
    0.36
     Knut
    0.36
    POSITIVE LOGITS
    樓
    1.80
    楼
    1.78
     lou
    1.29
    Lou
    1.27
     Lou
    1.26
    lou
    1.23
    楼主
    1.09
     building
    0.99
    Pav
    0.91
     Building
    0.89
    Activations Density 0.001%

    No Known Activations