© 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. 91237
    Prev
    Next
    INDEX
    Explanations

    video game titles

    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
    Refs
    0.52
    ராஜ்
    0.48
    ́i
    0.48
    ಾರ್ಥ
    0.48
    TZ
    0.47
    o
    0.47
    ｯ
    0.47
     met
    0.46
    MyDB
    0.46
    abhave
    0.46
    POSITIVE LOGITS
     सकती
    0.52
     могат
    0.52
    運び
    0.52
     jugement
    0.51
     Virginia
    0.50
    1
    0.49
    你可以
    0.48
     Pittsburgh
    0.48
     możesz
    0.48
    table
    0.47
    Activations Density 0.050%

    No Known Activations