© 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-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10517
    Prev
    Next
    INDEX
    Explanations

    portable, support, certified

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_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
     particip
    0.67
     empfe
    0.62
    𝑫
    0.60
     verdient
    0.58
     รวมถึง
    0.58
     植物
    0.58
     वनस्पती
    0.58
     medicina
    0.57
     restor
    0.57
     flavonoids
    0.57
    POSITIVE LOGITS
    ULL
    0.58
    (
    0.52
    ட்டான
    0.49
    Im
    0.49
    6
    0.49
    خ
    0.49
    σα
    0.48
    U
    0.48
    ца
    0.48
    AsString
    0.48
    Activations Density 0.031%

    No Known Activations