© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 203816
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and results

    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_25_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
    ekyll
    0.40
    疾患
    0.37
     поту
    0.37
    ্কর
    0.37
    indexBuffer
    0.37
     болез
    0.35
    পান
    0.34
    う
    0.34
     backgroundImg
    0.34
    地
    0.33
    POSITIVE LOGITS
     Suf
    0.40
     Preto
    0.39
     Invention
    0.39
     соответству
    0.38
     Rif
    0.38
     Likewise
    0.38
     T
    0.38
    avi
    0.37
     Illustrated
    0.37
     Consecutive
    0.37
    Activations Density 0.000%

    No Known Activations