© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29418
    Prev
    Next
    INDEX
    Explanations

    e-commerce, electronic

    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_10_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
    ک
    0.29
    ى
    0.26
    urang
    0.26
     gahet
    0.24
    ंप
    0.23
    или
    0.23
    ]#
    0.23
    𝗞
    0.22
    {
    0.22
    ],
    0.22
    POSITIVE LOGITS
     an
    0.24
     electrónico
    0.24
     aí
    0.24
     home
    0.23
     nó
    0.23
     dõi
    0.22
     soff
    0.22
     that
    0.22
     osmosis
    0.22
     it
    0.22
    Activations Density 0.014%

    No Known Activations