© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 52635
    Prev
    Next
    INDEX
    Explanations

    Geralt of Rivia

    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
     Protective
    0.26
     Protector
    0.25
    电压
    0.25
     胡
    0.25
     energized
    0.24
    舴
    0.24
     participação
    0.23
    ວິ
    0.23
     Harvest
    0.23
     presente
    0.23
    POSITIVE LOGITS
    atti
    0.28
    Was
    0.28
    Theme
    0.28
    agi
    0.28
    akin
    0.27
     нем
    0.27
     markedly
    0.27
    因而
    0.26
    /</
    0.26
     Сайт
    0.26
    Activations Density 0.000%

    No Known Activations