© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 217934
    Prev
    Next
    INDEX
    Explanations

    plant growth and yield metrics

    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_31_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
    ାଇ
    0.37
    āja
    0.36
     ligação
    0.35
    Connection
    0.35
    াচ্ছে
    0.35
    嘢
    0.34
     경
    0.34
     bundling
    0.34
     акы
    0.34
     CONNECTION
    0.34
    POSITIVE LOGITS
     tubes
    0.43
     regler
    0.38
     Tubes
    0.37
    OCE
    0.37
     Melinda
    0.36
     сложно
    0.36
    ouni
    0.36
    melt
    0.35
    涑
    0.35
     ಅಪಾಯ
    0.35
    Activations Density 0.001%

    No Known Activations