© 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. 3567
    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
    selling
    2.27
    त
    2.18
    ε
    2.16
    sb
    1.96
     informativa
    1.94
    要
    1.94
    ″
    1.90
    ∗</
    1.89
    sic
    1.80
    sure
    1.76
    POSITIVE LOGITS
     তবে
    2.17
    ლი
    2.00
     crying
    1.95
    uterine
    1.95
    electrolyte
    1.94
     بنابراین
    1.90
    그리고
    1.89
    plaintext
    1.87
    ול
    1.86
     Архиви
    1.79
    Activations Density 0.207%

    No Known Activations