© 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
    3. Gemma-3-4B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-16K
    7. 445
    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_12_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
     pemasaran
    0.16
     {:.
    0.16
     TInner
    0.15
    ."',
    0.15
    പ്പിച്ച്
    0.15
     tokopedia
    0.15
    ᚑ
    0.15
     derivada
    0.15
    jší
    0.15
    <unused1842>
    0.15
    POSITIVE LOGITS
    W
    0.18
    3
    0.18
     W
    0.17
    ER
    0.16
    H
    0.16
    K
    0.16
     Charlie
    0.16
    R
    0.16
    L
    0.16
    d
    0.16
    Activations Density 0.363%

    No Known Activations