© 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. 3241
    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
    ب
    3.88
    ed
    3.28
    л
    3.24
    on
    3.10
    та
    3.05
    an
    2.94
    问题
    2.88
    ০
    2.78
    ある
    2.74
    ת
    2.70
    POSITIVE LOGITS
     siendo
    2.64
    ızı
    2.59
    ᴇ
    2.59
    Prova
    2.53
    सी
    2.53
    llen
    2.52
    ны
    2.52
    ton
    2.47
    ᴀ
    2.47
     Хотя
    2.42
    Activations Density 0.006%

    No Known Activations