© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5831
    Prev
    Next
    INDEX
    Explanations

    simultaneously, meanwhile, correlation

    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_39_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
    स्टैंड
    0.40
    吧
    0.40
     Pric
    0.38
    रहे
    0.38
    ສະ
    0.38
     Тай
    0.37
     могу
    0.37
     সৌন্দর্য
    0.37
    styled
    0.37
    抽取
    0.37
    POSITIVE LOGITS
     Simultaneously
    0.37
    ⁃
    0.37
     uncorrelated
    0.35
     simultaneously
    0.34
     observational
    0.34
    ogenerated
    0.34
     Correlation
    0.33
     Meanwhile
    0.33
    bands
    0.33
    }/{
    0.32
    Activations Density 0.020%

    No Known Activations