© 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. 3754
    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
     carcinogenesis
    2.41
    setTo
    2.39
    popular
    2.37
    <bos>
    2.32
    不然
    2.31
    SHUNT
    2.30
    िस्ट
    2.29
    匱
    2.29
     merchandising
    2.27
     Reaktion
    2.23
    POSITIVE LOGITS
    ן
    2.86
    icionado
    2.34
    ні
    2.32
     ‫
    2.31
    ্ড
    2.28
    indsay
    2.28
     nevoie
    2.28
     বরং
    2.28
     subsequence
    2.27
    𝚔
    2.26
    Activations Density 0.041%

    No Known Activations