© 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. 3236
    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
    ز
    2.87
    न्त्र
    2.77
    う
    2.74
    ০
    2.73
    री
    2.69
    க
    2.52
    ยัง
    2.50
    ו
    2.48
    ς
    2.46
    रिडोर
    2.44
    POSITIVE LOGITS
    जीशन
    2.83
     debunk
    2.81
     plano
    2.66
    yacute
    2.62
    €™
    2.62
     mudd
    2.61
    是在
    2.58
     scolded
    2.54
    㧍
    2.53
    ˑ
    2.52
    Activations Density 0.005%

    No Known Activations