© 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
    2. Gemma-3-27B-IT
    3. 30-GEMMASCOPE-2-TRANSCODER-262K
    4. 51583
    Prev
    Next
    INDEX
    Explanations

    best recommendations

    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_30_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
    งาน
    0.41
    тельность
    0.41
    信
    0.38
    <unused345>
    0.36
    糹
    0.36
    ዋል
    0.36
     сообщение
    0.36
    })+\
    0.36
     信
    0.36
     किराने
    0.36
    POSITIVE LOGITS
     ఉన్నారు
    0.39
     بهترین
    0.39
     efficacement
    0.38
     optimally
    0.38
     ATT
    0.36
    han
    0.35
    ]{
    0.35
    Hein
    0.35
     Sent
    0.35
    medio
    0.35
    Activations Density 0.033%

    No Known Activations