© 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. 12-GEMMASCOPE-2-TRANSCODER-16K
    7. 331
    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
     she
    0.14
     her
    0.13
     then
    0.12
     become
    0.12
     (
    0.12
     he
    0.12
     his
    0.12
     rosé
    0.12
     crime
    0.12
     if
    0.12
    POSITIVE LOGITS
     ца
    0.14
    ządz
    0.14
    ༌
    0.14
    űkö
    0.14
    NIC
    0.14
    zyc
    0.14
    landır
    0.13
     প্রতিষ্ঠা
    0.13
    erasan
    0.13
     саны
    0.13
    Activations Density 3.329%

    No Known Activations