© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 261483
    Prev
    Next
    INDEX
    Explanations

    class IV shares

    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_22_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
     a
    0.38
    Bio
    0.36
    chrono
    0.36
    eta
    0.36
     bio
    0.36
     exceeded
    0.36
     Bio
    0.36
    csp
    0.36
    content
    0.35
    Chron
    0.35
    POSITIVE LOGITS
     \...
    0.38
     układ
    0.38
    Ꮁ
    0.35
     ปุ่ม
    0.35
     jinak
    0.34
    น์โหลด
    0.34
    甙
    0.34
    碇
    0.34
    кими
    0.34
     சீன
    0.34
    Activations Density 0.000%

    No Known Activations