© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9535
    Prev
    Next
    INDEX
    Explanations

    identifying objects in images

    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
    Rae
    0.41
     UHD
    0.36
    риа
    0.35
    薀
    0.35
    Sam
    0.34
     Rae
    0.34
    ળે
    0.34
    HD
    0.34
    clickHandler
    0.34
    ㄗ
    0.33
    POSITIVE LOGITS
     trong
    0.70
     nella
    0.68
     dalam
    0.66
     în
    0.65
    ใน
    0.65
     në
    0.64
     katika
    0.63
     nelle
    0.59
     ใน
    0.59
    dalam
    0.55
    Activations Density 0.152%

    No Known Activations