© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8568
    Prev
    Next
    INDEX
    Explanations

    carpets, rugs, blankets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    s
    2.19
    sic
    2.17
     grim
    2.03
    ล์
    1.95
    ceil
    1.86
    klar
    1.85
    ς
    1.79
    sag
    1.75
    и
    1.75
    鐘
    1.73
    POSITIVE LOGITS
    ة
    2.25
     encuentra
    2.19
     porches
    2.13
     worksheets
    2.09
    বিষ্য
    2.01
    可以看到
    1.99
     carpeting
    1.98
     homomorphisms
    1.98
     المقد
    1.97
     چنان
    1.96
    Activations Density 0.027%

    No Known Activations