© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242550
    Prev
    Next
    INDEX
    Explanations

    FROM table name

    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_40_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
     Managed
    0.39
     CI
    0.38
    ทรวง
    0.37
    PCI
    0.37
     সংসদে
    0.36
    ꉂ
    0.36
    iatrics
    0.36
    سون
    0.36
    Apache
    0.36
     fresh
    0.36
    POSITIVE LOGITS
    ㄇ
    0.39
     देकर
    0.38
     போட
    0.37
    办事
    0.37
     பொருட்க
    0.37
     Shit
    0.37
     teclas
    0.36
     handouts
    0.36
     सेल्स
    0.36
    ÇÃO
    0.36
    Activations Density 0.004%

    No Known Activations