© 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. 2840
    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
    ся
    1.31
    weise
    1.24
    ن
    1.22
    le
    1.15
    可能性
    1.14
    mitter
    1.12
     वहीं
    1.11
    कांग्रेस
    1.11
    ्ट
    1.11
    ून
    1.11
    POSITIVE LOGITS
     stave
    1.15
     centrifugation
    1.09
     stated
    1.09
    ncol
    1.08
    不
    1.08
     nrow
    1.08
    epochs
    1.07
    ηση
    1.06
    tul
    1.05
    ि
    1.03
    Activations Density 0.016%

    No Known Activations