© 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. 658
    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
    er
    2.12
    い
    1.71
     ज़र
    1.65
    дравствуйте
    1.65
    erade
    1.55
    withstanding
    1.51
    ੀ
    1.51
    䏲
    1.48
    Uppercase
    1.45
    "—
    1.38
    POSITIVE LOGITS
    rences
    1.66
    ções
    1.61
     لد
    1.58
    ina
    1.52
     aunque
    1.52
     में
    1.52
     ใน
    1.52
     से
    1.51
    𝒗
    1.51
     तसेच
    1.51
    Activations Density 0.981%

    No Known Activations