© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173243
    Prev
    Next
    INDEX
    Explanations

    numerical values and quantities

    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_20_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
     recher
    0.40
     myc
    0.40
     genres
    0.39
    绽
    0.39
    abbanti
    0.39
    搜尋
    0.39
     prestig
    0.39
    semanticweb
    0.39
     nghiên
    0.38
    wm
    0.38
    POSITIVE LOGITS
    াড়ার
    0.44
    BOW
    0.42
    하지만
    0.41
     spikes
    0.39
     joyas
    0.39
     bandages
    0.38
    वेशन
    0.37
    뻤
    0.37
     foothills
    0.37
    PAK
    0.36
    Activations Density 0.001%

    No Known Activations