© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107416
    Prev
    Next
    INDEX
    Explanations

    legal and ethical misconduct

    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_1_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
    ни
    1.25
    ه
    1.13
    nál
    1.11
    ações
    1.02
    ر
    1.02
    но
    1.01
    nél
    1.00
    ний
    0.98
    ीय
    0.96
    กว่า
    0.95
    POSITIVE LOGITS
    та
    1.17
    ի
    1.16
     a
    1.06
    '
    1.05
     are
    1.00
    的多
    0.95
    的外
    0.93
    מ
    0.92
     l
    0.91
    的产品
    0.88
    Activations Density 0.001%

    No Known Activations