© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 160292
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    ৫
    0.98
     to
    0.93
    ள்ளனர்
    0.92
     referendum
    0.89
    し
    0.88
    的安全
    0.87
     highlighted
    0.86
     recuper
    0.86
     inciner
    0.86
     showering
    0.86
    POSITIVE LOGITS
    <0x80>
    1.09
    ة
    1.06
    ى
    1.05
    0
    1.01
    1.01
    sembles
    1.00
    la
    0.98
    ان
    0.98
    al
    0.96
    Enlaces
    0.96
    Activations Density 0.000%

    No Known Activations