© 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-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1432
    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
     rela
    3.05
    ════
    2.97
     tensors
    2.90
    くら
    2.83
    quarters
    2.78
    ⎣
    2.75
    ירים
    2.74
    де
    2.66
     doubts
    2.61
     itulah
    2.59
    POSITIVE LOGITS
    ون
    2.90
    숲
    2.77
    σία
    2.73
    ্যা
    2.66
    нку
    2.65
    nement
    2.60
    fadeIn
    2.60
    มือ
    2.59
    ists
    2.54
    ر
    2.52
    Activations Density 0.084%

    No Known Activations