© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 2124
    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
     incluidas
    2.65
     uncoated
    2.59
     불구하고
    2.43
     atrav
    2.40
    heastern
    2.35
    itized
    2.30
    ▯
    2.29
    footed
    2.28
     públicas
    2.27
    𝓃
    2.27
    POSITIVE LOGITS
    र
    2.82
    請問
    2.48
    Orbit
    2.43
    ম
    2.37
    ン
    2.26
    ため
    2.26
    сть
    2.20
    ز
    2.19
    ς
    2.19
    ൽ
    2.19
    Activations Density 0.075%

    No Known Activations