© 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. 2893
    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
     грн
    2.60
     steeply
    2.58
    म्यान
    2.43
     noqa
    2.39
    ता
    2.36
    عرف
    2.33
    ྜ
    2.33
    リューム
    2.32
    ০০
    2.27
    єї
    2.26
    POSITIVE LOGITS
    스러운
    3.17
    스러
    2.98
    스럽
    2.56
    s
    2.55
    δήποτε
    2.55
     Lorentzian
    2.53
     Posteriormente
    2.50
    by
    2.48
    ء
    2.44
    ependent
    2.41
    Activations Density 0.016%

    No Known Activations