© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220585
    Prev
    Next
    INDEX
    Explanations

    plant pests and diseases

    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
     insulin
    0.45
     cognit
    0.41
     Insulation
    0.39
    鄙
    0.39
     intenz
    0.39
     amort
    0.38
     Insulin
    0.38
     Lower
    0.36
     intent
    0.36
    нува
    0.36
    POSITIVE LOGITS
    航
    0.42
     نر
    0.41
    엎
    0.41
    lemb
    0.40
    पक्ष
    0.40
    odesmium
    0.40
     எது
    0.39
     StringBuilder
    0.39
    hoppers
    0.38
     lesbians
    0.38
    Activations Density 0.003%

    No Known Activations