© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15884
    Prev
    Next
    INDEX
    Explanations

    camel, goat, llama wool

    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_40_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
     अंडे
    0.42
     oyster
    0.42
    ட்சத்திர
    0.41
     ostrich
    0.41
     Oyster
    0.41
    АС
    0.39
    鲲
    0.39
     selectTable
    0.38
     telur
    0.38
    儷
    0.37
    POSITIVE LOGITS
     tent
    0.59
    Tent
    0.58
     tents
    0.57
    tent
    0.54
     Tent
    0.51
    テント
    0.48
    Hair
    0.44
     hair
    0.43
     ropes
    0.42
    Curt
    0.41
    Activations Density 0.082%

    No Known Activations