© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260751
    Prev
    Next
    INDEX
    Explanations

    security patch updates

    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
     gly
    0.20
     Understanding
    0.19
    Utf
    0.18
    珐
    0.18
     mainly
    0.18
    ースト
    0.18
     zrozum
    0.18
    Understanding
    0.18
    ื่ม
    0.18
    明白了
    0.18
    POSITIVE LOGITS
     stats
    0.25
    repaint
    0.23
     статисти
    0.23
     usług
    0.23
    ajada
    0.22
     د
    0.22
     estadística
    0.21
    लीट
    0.21
    stats
    0.20
    Suggested
    0.20
    Activations Density 0.011%

    No Known Activations