© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 125005
    Prev
    Next
    INDEX
    Explanations

    judicial appointments

    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_3_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
    ني
    0.84
    ن
    0.82
    ন
    0.79
    ة
    0.78
    ர
    0.77
    كل
    0.75
     براي
    0.74
    ン
    0.73
    رك
    0.73
    asyonu
    0.72
    POSITIVE LOGITS
    in
    0.92
    m
    0.91
    to
    0.83
    j
    0.80
    v
    0.79
    ur
    0.78
    f
    0.78
     inpatient
    0.77
     attorney
    0.72
     akhir
    0.70
    Activations Density 0.000%

    No Known Activations