© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 3012
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    ℎ
    2.73
     hashTable
    2.72
    अन्य
    2.69
    𝑒
    2.67
    Fortunately
    2.65
    ով
    2.63
    screenshots
    2.62
    unsplash
    2.61
    徃
    2.59
    >>>>>>>>
    2.57
    POSITIVE LOGITS
    س
    3.45
    ers
    3.41
    ش
    3.33
    t
    3.20
    ेश
    2.84
    ع
    2.67
    اة
    2.55
    ів
    2.51
    ie
    2.37
    是什麼
    2.31
    Activations Density 0.076%

    No Known Activations