© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 59204
    Prev
    Next
    INDEX
    Explanations

    Pacific Ocean

    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
     CRP
    0.58
    har
    0.53
     ทำให้
    0.53
     Textile
    0.52
     Light
    0.52
    ol
    0.51
    h
    0.50
     تھے۔
    0.50
    pon
    0.49
    हार्
    0.49
    POSITIVE LOGITS
    ])
    0.64
    udarstvennyj
    0.55
     bifurcation
    0.54
     arbre
    0.54
    ф
    0.53
     animali
    0.52
     nuts
    0.52
    就不
    0.52
     inhibitory
    0.51
     arbres
    0.51
    Activations Density 0.001%

    No Known Activations