© 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-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48212
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_width_262k_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
    ikala
    0.47
     ускори
    0.47
    𝗞
    0.46
    LPTMR
    0.46
    κ
    0.46
     বৎ
    0.45
    鲽
    0.44
     terzo
    0.43
    𝗕
    0.43
    ujen
    0.42
    POSITIVE LOGITS
    ,
    0.53
    ر
    0.52
     е
    0.47
     (
    0.46
     में
    0.46
     à
    0.45
     dil
    0.44
    CompanyName
    0.43
    र
    0.43
     occasions
    0.42
    Activations Density 0.000%

    No Known Activations