© 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. 215327
    Prev
    Next
    INDEX
    Explanations

    collectible figures and statues

    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
     coupe
    0.35
     Prodig
    0.35
     γνω
    0.33
    🍾
    0.32
     coupes
    0.31
     watchdog
    0.30
    🏎
    0.30
     giphy
    0.29
    igueur
    0.29
     Coupe
    0.29
    POSITIVE LOGITS
     یو
    0.32
    北美
    0.31
     amal
    0.30
     Yemek
    0.30
    韮
    0.29
     bữa
    0.29
    playable
    0.28
    皿
    0.28
    蘆
    0.27
     വിദ
    0.27
    Activations Density 0.001%

    No Known Activations