© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 5236
    Prev
    Next
    INDEX
    Explanations

    time and pay

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
    跳
    0.40
    体が
    0.37
     sağlı
    0.36
    Cla
    0.36
     penny
    0.36
    ynth
    0.36
     négy
    0.35
     слов
    0.35
    EDY
    0.34
    Penny
    0.34
    POSITIVE LOGITS
    itare
    0.44
    ihull
    0.40
    沣
    0.40
     Hours
    0.40
     uninstall
    0.40
     Astr
    0.39
     time
    0.39
     paid
    0.39
     Time
    0.39
     Wessex
    0.39
    Activations Density 0.075%

    No Known Activations