© 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. 1367
    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
    ة
    2.99
     ";"
    2.36
     כך
    2.30
    毕竟
    2.09
    en
    2.03
     Purpose
    1.93
    عرف
    1.93
    фта
    1.90
    aruh
    1.89
    et
    1.89
    POSITIVE LOGITS
    v
    2.22
    and
    2.09
    😂😂
    1.94
    milliseconds
    1.93
    ле
    1.89
    ০০
    1.86
     nemus
    1.85
    to
    1.85
     Ges
    1.82
    intersection
    1.80
    Activations Density 0.116%

    No Known Activations