© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 245588
    Prev
    Next
    INDEX
    Explanations

    satisfy or satisfy upon

    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_40_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
    acias
    0.37
    elementProp
    0.37
    Glue
    0.36
     कॉम्प
    0.36
    किम
    0.35
    망
    0.35
    χεία
    0.34
    ettamente
    0.34
    ającym
    0.34
    
    0.34
    POSITIVE LOGITS
     satisfy
    2.00
     satisfies
    1.86
    满足
    1.79
    Satisf
    1.79
     satisfying
    1.78
     Satisf
    1.77
     satisfied
    1.71
     удовлетво
    1.71
    滿足
    1.65
    satisf
    1.61
    Activations Density 0.191%

    No Known Activations