© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 2-GEMMASCOPE-2-TRANSCODER-16K
    4. 166
    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
    persons
    0.38
     ventricle
    0.35
    blowing
    0.35
     安
    0.35
     તેમણે
    0.35
    Wires
    0.35
     इससे
    0.35
    entropic
    0.35
     તેમને
    0.34
    wires
    0.34
    POSITIVE LOGITS
    न
    0.44
    ر
    0.43
    й
    0.40
    Пре
    0.38
    ع
    0.37
     neuesten
    0.36
    ال
    0.36
    Ко
    0.36
    в
    0.34
    н
    0.34
    Activations Density 0.190%

    No Known Activations