© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209781
    Prev
    Next
    INDEX
    Explanations

    above or below

    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_20_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
    sext
    0.27
     Sensing
    0.27
     McEl
    0.27
     hoch
    0.27
    ഠ
    0.26
     Schmidt
    0.26
     Brun
    0.25
    BackPressed
    0.25
    ular
    0.24
    ters
    0.24
    POSITIVE LOGITS
    म्मा
    0.28
     организма
    0.28
     يتيمه
    0.28
    基準
    0.27
     הזה
    0.27
    Amar
    0.27
     ყველა
    0.27
    籶
    0.27
     уче
    0.27
    기준
    0.27
    Activations Density 0.001%

    No Known Activations