© 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. 2982
    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
    ᴇ
    1.54
    𝗲
    1.43
    تال
    1.37
    inien
    1.32
    лива
    1.32
    ld
    1.32
    ី
    1.30
    st
    1.29
    ัล
    1.28
     mannitol
    1.28
    POSITIVE LOGITS
    cribe
    1.45
    quele
    1.37
     fanfare
    1.33
    তারপর
    1.32
    দের
    1.31
    getWindow
    1.25
    त्मक
    1.24
     mailed
    1.24
    ided
    1.22
     карти
    1.21
    Activations Density 0.019%

    No Known Activations