© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 3865
    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
    appendix
    1.86
    \{\
    1.80
     wenige
    1.74
    \{(
    1.71
    ot
    1.71
    िंग
    1.69
    ൂ
    1.67
    ণিজ্য
    1.64
    ណ៍
    1.63
    mdash
    1.59
    POSITIVE LOGITS
    en
    2.19
     avis
    2.14
    sı
    1.95
    g
    1.89
    கோ
    1.85
    கிறது
    1.74
    dır
    1.72
    ための
    1.70
    পক্ষ
    1.68
    ಇ
    1.68
    Activations Density 0.011%

    No Known Activations