© 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. 164512
    Prev
    Next
    INDEX
    Explanations

    Fullmetal Alchemist

    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
    Incremental
    0.40
    im
    0.38
    incremental
    0.37
     روا
    0.35
    ین
    0.35
     hvis
    0.34
    ح
    0.34
    enment
    0.34
     مگر
    0.33
     cursory
    0.33
    POSITIVE LOGITS
     SalesLT
    0.50
     Yourself
    0.44
     Trade
    0.44
    ađ
    0.43
     শিল্পী
    0.43
     Certains
    0.42
     Закон
    0.41
    윕
    0.41
     nad
    0.41
     Sneakers
    0.41
    Activations Density 0.002%

    No Known Activations