© 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. 4227
    Prev
    Next
    INDEX
    Explanations

    CPU model numbers and generations

    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
    Tra
    0.46
     Prerequisites
    0.43
     Tra
    0.40
     tra
    0.39
     prerequisites
    0.37
    Prepar
    0.37
    トラ
    0.36
    -->'
    0.35
     calc
    0.35
     тра
    0.34
    POSITIVE LOGITS
    boxylic
    0.49
    ric
    0.43
    myItem
    0.39
    osseum
    0.38
    scenario
    0.38
     effort
    0.37
     मल्टी
    0.37
    yk
    0.36
     Coffee
    0.36
     Moe
    0.36
    Activations Density 0.058%

    No Known Activations