© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 60883
    Prev
    Next
    INDEX
    Explanations

    new

    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_59_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
     know
    2.08
     Know
    1.92
    Know
    1.91
    know
    1.77
     knows
    1.55
    知
    1.46
     Knows
    1.42
     KNOW
    1.41
    知道
    1.27
     знает
    1.24
    POSITIVE LOGITS
    new
    1.10
     new
    1.01
     নতুন
    0.84
     புதிய
    0.78
     نئے
    0.78
     പുതിയ
    0.77
     K
    0.76
     جديد
    0.75
     nieuwe
    0.73
     yeni
    0.72
    Activations Density 0.025%

    No Known Activations