© 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. 2531
    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
    ′
    1.59
    <unused1896>
    1.40
     freaking
    1.33
    ′,
    1.31
    х
    1.30
     trove
    1.26
    ^{\
    1.24
     मंस
    1.24
     Learned
    1.20
     coerc
    1.14
    POSITIVE LOGITS
    ために
    1.62
    之路
    1.40
    𝗻
    1.38
    𝗶
    1.33
     modulo
    1.31
    buscar
    1.29
    𝗺
    1.28
     dataGridView
    1.28
     删除
    1.27
    yw
    1.27
    Activations Density 0.159%

    No Known Activations