© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60395
    Prev
    Next
    INDEX
    Explanations

    inspiring people and things

    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
    five
    0.60
     rued
    0.60
     beş
    0.58
     compatriots
    0.57
     अवै
    0.57
     otras
    0.55
    व
    0.55
    ה
    0.54
     cuatro
    0.54
    ந
    0.54
    POSITIVE LOGITS
     Israël
    0.61
     gäller
    0.57
    管理局
    0.57
    ibilités
    0.57
    ）
    0.57
    ě
    0.56
     illustrate
    0.55
    \...
    0.54
    åller
    0.54
    ā
    0.54
    Activations Density 0.002%

    No Known Activations