© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89433
    Prev
    Next
    INDEX
    Explanations

    calling for

    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_11_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
    น์
    0.58
    लित
    0.52
    ल
    0.52
     पश्चिम
    0.50
     प्र
    0.48
    ้
    0.48
    าก
    0.48
     Destination
    0.48
     اولین
    0.48
     West
    0.48
    POSITIVE LOGITS
    {
    0.55
    borg
    0.54
    <td>
    0.53
    been
    0.53
     ζωή
    0.52
     had
    0.50
    t
    0.50
     شيء
    0.49
    um
    0.49
     Ελλά
    0.48
    Activations Density 0.003%

    No Known Activations