© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 83208
    Prev
    Next
    INDEX
    Explanations

    stress, debt, security, background

    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_29_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
     والم
    0.37
    UnitTest
    0.36
     ומ
    0.35
    Vendor
    0.34
     и
    0.34
     및
    0.33
     و
    0.33
    គ្មាន
    0.33
    쟤
    0.32
     și
    0.32
    POSITIVE LOGITS
     massaging
    0.38
    봅
    0.37
    比如说
    0.37
     barbeque
    0.37
     Porém
    0.36
     Međutim
    0.36
     propane
    0.35
    ເອ
    0.35
     etcétera
    0.35
     pruned
    0.35
    Activations Density 0.002%

    No Known Activations