© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 149313
    Prev
    Next
    INDEX
    Explanations

    events or periods

    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
     ='
    0.46
    .(\
    0.40
     растение
    0.40
    ((\
    0.39
    ipio
    0.39
    =(\
    0.39
    機構
    0.38
     ώ
    0.38
    =(-
    0.38
     Институт
    0.37
    POSITIVE LOGITS
     prep
    1.23
     Prep
    0.96
     weekend
    0.94
    prep
    0.94
    Prep
    0.93
    weekend
    0.80
     cycle
    0.75
    Weekend
    0.73
     cycles
    0.72
     weekends
    0.67
    Activations Density 0.007%

    No Known Activations