© 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. 2327
    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
    к
    3.67
    י
    3.48
    ל
    3.05
    i
    3.04
    न
    2.93
    graphicx
    2.84
    kath
    2.84
    cua
    2.84
    кте
    2.82
    hydrogen
    2.81
    POSITIVE LOGITS
    اں
    3.24
    𝐩
    3.21
    𝐬
    3.17
    𝐚
    3.15
    𝐲
    3.14
    ிய
    2.95
    𝐨
    2.83
    См
    2.71
    𝐭
    2.68
    सर
    2.67
    Activations Density 0.104%

    No Known Activations