© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10201
    Prev
    Next
    INDEX
    Explanations

    magento 2 extension

    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_13_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
    Erd
    0.49
    François
    0.46
    衰
    0.46
    Ret
    0.45
    𝙊
    0.45
    Reform
    0.45
    ធម្ម
    0.45
    ድ
    0.44
    Er
    0.44
    Zum
    0.44
    POSITIVE LOGITS
     {$
    0.55
     szeptember
    0.52
     Accra
    0.49
     Chef
    0.49
     Bupati
    0.49
     службы
    0.48
     nouvelle
    0.47
     offrant
    0.47
     itp
    0.47
     broj
    0.46
    Activations Density 0.002%

    No Known Activations