© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212229
    Prev
    Next
    INDEX
    Explanations

    IntelliSense

    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_5_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
    ເຄື່ອງ
    1.26
    고
    1.20
    𝗺
    1.18
    면
    1.13
    맞
    1.09
    못
    1.09
    머
    1.05
    말
    1.03
    XII
    1.02
    ம
    1.02
    POSITIVE LOGITS
    ى
    1.27
    ية
    1.09
     an
    1.01
     in
    0.94
     η
    0.94
     impair
    0.90
     leta
    0.90
    kons
    0.90
    ки
    0.89
     ehrlich
    0.89
    Activations Density 0.000%

    No Known Activations