© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 204331
    Prev
    Next
    INDEX
    Explanations

    find documents or duplicates

    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_6_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
    ne
    1.29
    la
    1.28
    re
    1.19
    oh
    1.15
    t
    1.14
    te
    1.08
    ra
    1.07
    rt
    1.02
    0
    1.00
     E
    0.96
    POSITIVE LOGITS
    ا
    1.06
    ികി
    0.98
    ా
    0.91
    اوی
    0.91
     масте
    0.89
    ARMA
    0.88
    مة
    0.87
     assumptive
    0.86
    γρά
    0.85
     atheros
    0.84
    Activations Density 0.005%

    No Known Activations