© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 928
    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
    ../
    3.40
    личие
    2.81
     Nella
    2.63
    ての
    2.43
    ej
    2.40
    는
    2.40
    netstandard
    2.38
    ió
    2.36
    ist
    2.34
    zelfde
    2.33
    POSITIVE LOGITS
     effettu
    2.80
     suur
    2.79
     mortars
    2.63
    न
    2.52
     refrain
    2.52
    াবদ্ধ
    2.46
    א
    2.35
    ся
    2.27
     edific
    2.26
    in
    2.24
    Activations Density 0.228%

    No Known Activations