© 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. 2120
    Prev
    Next
    INDEX
    Explanations

    trees and surgery

    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
     shrub
    0.48
     ring
    0.46
     shrubs
    0.44
    Ring
    0.44
     pea
    0.41
    蕉
    0.40
     Ring
    0.39
     verv
    0.39
    trees
    0.39
     bushes
    0.38
    POSITIVE LOGITS
    γγρα
    0.43
    спекти
    0.38
     коля
    0.38
     Trademark
    0.38
     Umsatz
    0.38
    পালের
    0.37
     regeneration
    0.37
     compart
    0.36
    誐
    0.36
     Интере
    0.36
    Activations Density 0.030%

    No Known Activations